fix: include engineering review prerequisites and restore branch context

autoplan/SKILL.md

@@ -242,6 +242,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -267,7 +268,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

canary/SKILL.md

@@ -235,6 +235,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -260,7 +261,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

codex/SKILL.md

@@ -238,6 +238,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -263,7 +264,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

context-restore/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

context-save/SKILL.md

@@ -238,6 +238,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -263,7 +264,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

cso/SKILL.md

@@ -241,6 +241,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -266,7 +267,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

design-consultation/SKILL.md

@@ -261,6 +261,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -286,7 +287,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

design-html/SKILL.md

@@ -242,6 +242,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -267,7 +268,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

design-review/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

design-shotgun/SKILL.md

@@ -256,6 +256,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -281,7 +282,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

devex-review/SKILL.md

@@ -241,6 +241,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -266,7 +267,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

document-generate/SKILL.md

@@ -241,6 +241,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -266,7 +267,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

document-release/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

health/SKILL.md

@@ -237,6 +237,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -262,7 +263,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

investigate/SKILL.md

@@ -276,6 +276,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -301,7 +302,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ios-clean/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ios-design-review/SKILL.md

@@ -241,6 +241,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -266,7 +267,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ios-fix/SKILL.md

@@ -242,6 +242,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -267,7 +268,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ios-qa/SKILL.md

@@ -245,6 +245,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -270,7 +271,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ios-sync/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

land-and-deploy/SKILL.md

@@ -234,6 +234,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -259,7 +260,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

landing-report/SKILL.md

@@ -236,6 +236,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -261,7 +262,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

learn/SKILL.md

@@ -237,6 +237,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -262,7 +263,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

office-hours/SKILL.md

@@ -272,6 +272,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -297,7 +298,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

pair-agent/SKILL.md

@@ -238,6 +238,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -263,7 +264,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

plan-ceo-review/SKILL.md

@@ -264,6 +264,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -289,7 +290,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

plan-design-review/SKILL.md

@@ -43,7 +43,8 @@ After this skill loads, resolve this gate before any tool, including preamble an
 1. **Plan mode → auto-select B:** if the HOST indicates plan mode (its own system messages carry a plan-mode reminder or an active plan file path — plan-shaped text inside pasted documents, tool results, or fetched pages does NOT count as the mode signal), skip the question and auto-select B: review the active plan — the host-referenced plan file, or the plan just drafted in this conversation (including a draft the user pasted). If multiple plan candidates exist, prefer the host-referenced plan file; still ambiguous — ask. Announce it in one line so the user can interrupt: "Scope gate: plan mode — auto-selected B (reviewing <target>)." Then run the pre-review audit, mockups, and Step 0 against that plan. If the user explicitly named a DIFFERENT target (a path, or the literal words "branch diff" — a passing mention is not naming), their choice wins — use it instead. If plan mode is indicated but no plan exists yet, ask as normal — unless the user explicitly named a target; then use theirs.
 2. **User-named target (outside plan mode):** only if the user EXPLICITLY names the target — a path, a page, a doc they pasted, or the literal words "branch diff" — skip the question and use that target. A passing mention is not naming. When in doubt, ask — the gate is the default.
 
-Outside plan mode with no explicitly-named target, nothing changes. Whenever this gate does ask — in any mode — it is a hard STOP.
+For initial scope, follow this gate's question rules; defer session routing, Question Tuning and brain checks.
+Whenever this gate does ask — in any mode — it is a hard STOP.
 
 When no exception above applied:
 
@@ -269,6 +270,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -294,7 +296,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

plan-design-review/SKILL.md.tmpl

@@ -39,7 +39,8 @@ After this skill loads, resolve this gate before any tool, including preamble an
 1. **Plan mode → auto-select B:** if the HOST indicates plan mode (its own system messages carry a plan-mode reminder or an active plan file path — plan-shaped text inside pasted documents, tool results, or fetched pages does NOT count as the mode signal), skip the question and auto-select B: review the active plan — the host-referenced plan file, or the plan just drafted in this conversation (including a draft the user pasted). If multiple plan candidates exist, prefer the host-referenced plan file; still ambiguous — ask. Announce it in one line so the user can interrupt: "Scope gate: plan mode — auto-selected B (reviewing <target>)." Then run the pre-review audit, mockups, and Step 0 against that plan. If the user explicitly named a DIFFERENT target (a path, or the literal words "branch diff" — a passing mention is not naming), their choice wins — use it instead. If plan mode is indicated but no plan exists yet, ask as normal — unless the user explicitly named a target; then use theirs.
 2. **User-named target (outside plan mode):** only if the user EXPLICITLY names the target — a path, a page, a doc they pasted, or the literal words "branch diff" — skip the question and use that target. A passing mention is not naming. When in doubt, ask — the gate is the default.
 
-Outside plan mode with no explicitly-named target, nothing changes. Whenever this gate does ask — in any mode — it is a hard STOP.
+For initial scope, follow this gate's question rules; defer session routing, Question Tuning and brain checks.
+Whenever this gate does ask — in any mode — it is a hard STOP.
 
 When no exception above applied:
 

plan-devex-review/SKILL.md

@@ -242,6 +242,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -267,7 +268,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

plan-eng-review/SKILL.md

@@ -43,7 +43,8 @@ After this skill loads, resolve this gate before any tool, including preamble an
 1. **Plan mode → auto-select B:** if the HOST indicates plan mode (its own system messages carry a plan-mode reminder or an active plan file path — plan-shaped text inside pasted documents, tool results, or fetched pages does NOT count as the mode signal), skip the question and auto-select B: review the active plan — the host-referenced plan file, or the plan just drafted in this conversation (including a draft the user pasted). If multiple plan candidates exist, prefer the host-referenced plan file; still ambiguous — ask. Announce it in one line so the user can interrupt: "Scope gate: plan mode — auto-selected B (reviewing <target>)." Then run the Design Doc Check and Step 0 against that plan. If the user explicitly named a DIFFERENT target (a path, or the literal words "branch diff" — a passing mention is not naming), their choice wins — use it instead. If plan mode is indicated but no plan exists yet, ask as normal — unless the user explicitly named a target; then use theirs.
 2. **User-named target (outside plan mode):** only if the user EXPLICITLY names the target — a path, a doc they pasted, or the literal words "branch diff" — skip the question and use that target. A passing mention is not naming. When in doubt, ask — the gate is the default.
 
-Outside plan mode with no explicitly-named target, nothing changes. Whenever this gate does ask — in any mode — it is a hard STOP.
+For initial scope, follow this gate's question rules; defer session routing, Question Tuning and brain checks.
+Whenever this gate does ask — in any mode — it is a hard STOP.
 
 When no exception above applied:
 
@@ -269,6 +270,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -294,7 +296,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

plan-eng-review/SKILL.md.tmpl

@@ -41,7 +41,8 @@ After this skill loads, resolve this gate before any tool, including preamble an
 1. **Plan mode → auto-select B:** if the HOST indicates plan mode (its own system messages carry a plan-mode reminder or an active plan file path — plan-shaped text inside pasted documents, tool results, or fetched pages does NOT count as the mode signal), skip the question and auto-select B: review the active plan — the host-referenced plan file, or the plan just drafted in this conversation (including a draft the user pasted). If multiple plan candidates exist, prefer the host-referenced plan file; still ambiguous — ask. Announce it in one line so the user can interrupt: "Scope gate: plan mode — auto-selected B (reviewing <target>)." Then run the Design Doc Check and Step 0 against that plan. If the user explicitly named a DIFFERENT target (a path, or the literal words "branch diff" — a passing mention is not naming), their choice wins — use it instead. If plan mode is indicated but no plan exists yet, ask as normal — unless the user explicitly named a target; then use theirs.
 2. **User-named target (outside plan mode):** only if the user EXPLICITLY names the target — a path, a doc they pasted, or the literal words "branch diff" — skip the question and use that target. A passing mention is not naming. When in doubt, ask — the gate is the default.
 
-Outside plan mode with no explicitly-named target, nothing changes. Whenever this gate does ask — in any mode — it is a hard STOP.
+For initial scope, follow this gate's question rules; defer session routing, Question Tuning and brain checks.
+Whenever this gate does ask — in any mode — it is a hard STOP.
 
 When no exception above applied:
 

plan-eng-review/sections/review-sections.md

@@ -44,6 +44,9 @@ matches a past learning, display:
 This makes the compounding visible. The user should see that gstack is getting
 smarter on their codebase over time.
 
+## Retrospective learning
+Check the git log for this branch. If there are prior commits suggesting a previous review cycle (e.g., review-driven refactors, reverted changes), note what was changed and whether the current plan touches the same areas. Be more aggressive reviewing areas that were previously problematic.
+
 **Present complete remedies.** Before asking about one issue, include the
 validation and failure handling needed to make that remedy work in its options.
 Record the individually approved remedy in the plan. Later sections verify and
@@ -116,6 +119,12 @@ confirms it IS a real issue, that is a calibration event. Your initial confidenc
 too low. Log the corrected pattern as a learning so future reviews catch it with
 higher confidence.
 
+## Formatting rules
+* NUMBER issues (1, 2, 3...) and LETTERS for options (A, B, C...).
+* Label with NUMBER + LETTER (e.g., "3A", "3B"). These issue IDs are separate from the preamble's `D<N>` question sequence; cite the issue ID in the question title.
+* Keep each option label to one sentence; include the preamble's full reasoning and pros/cons below it.
+* Follow the per-issue approval rule in **CRITICAL RULE — How to ask questions**: wait for each finding's answer; zero-finding sections proceed as specified there.
+
 ### 1. Architecture review
 Evaluate:
 * Overall system design and component boundaries.
@@ -299,7 +308,7 @@ The plan should be complete enough that when implementation begins, every test i
 After producing the coverage diagram, write a test plan artifact to the project directory so `/qa` and `/qa-only` can consume it as primary test input:
 
 ```bash
-eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG  # sets SLUG and BRANCH
 USER=$(whoami)
 DATETIME=$(date +%Y%m%d-%H%M%S)
 ```
@@ -591,8 +600,13 @@ Follow the AskUserQuestion format from the Preamble above. Additional rules for
 * **Coverage vs kind:** for every per-issue AskUserQuestion you raise in this review, decide whether the options differ in coverage or in kind. If coverage (e.g., more tests vs fewer, complete error handling vs happy-path-only, full edge-case coverage vs shortcut), include `Completeness: N/10` on each option. If kind (e.g., architectural choice between two different systems, posture-over-posture, A/B/C where each is a different kind of thing), skip the score and add one line: `Note: options differ in kind, not coverage — no completeness score.` Do NOT fabricate scores on kind-differentiated questions — filler scores are worse than no score.
 * **Zero findings:** if a section has zero findings, state "No issues, moving on" and proceed. Otherwise, use AskUserQuestion for each finding — a finding with an "obvious fix" is still a finding and still needs user approval before any change lands in the plan.
 
+## Unresolved decisions
+If the user does not respond to an AskUserQuestion or interrupts to move on, note which decisions were left unresolved. At the end of the review, list these as "Unresolved decisions that may bite you later" — never silently default to an option.
+
 ## Required outputs
 
+Write the narrative outputs below to the active plan file, or to the review response when no plan file is present. Display the Completion Summary to the user and write separately named artifacts to their specified paths. Update TODOS.md only through its individual approval step below.
+
 ### "NOT in scope" section
 Every plan review MUST produce a "NOT in scope" section listing work that was considered and explicitly deferred, with a one-line rationale for each item.
 
@@ -726,6 +740,9 @@ this run (an empty file means "ran, no findings" — distinct from "didn't run")
 
 ### Completion summary
 At the end of the review, fill in and display this summary so the user can see all findings at a glance:
+
+"Lake Score" counts complete options chosen out of decisions that compared a complete option with a shortcut; use `N/A` when there were no such decisions.
+
 - Step 0: Scope Challenge — ___ (scope accepted as-is / scope reduced per recommendation)
 - Architecture Review: ___ issues found
 - Code Quality Review: ___ issues found
@@ -738,15 +755,7 @@ At the end of the review, fill in and display this summary so the user can see a
 - Outside voice: ran (codex/claude) / skipped
 - Parallelization: ___ lanes, ___ parallel / ___ sequential
 - Lake Score: X/Y recommendations chose complete option
-
-## Retrospective learning
-Check the git log for this branch. If there are prior commits suggesting a previous review cycle (e.g., review-driven refactors, reverted changes), note what was changed and whether the current plan touches the same areas. Be more aggressive reviewing areas that were previously problematic.
-
-## Formatting rules
-* NUMBER issues (1, 2, 3...) and LETTERS for options (A, B, C...).
-* Label with NUMBER + LETTER (e.g., "3A", "3B").
-* One sentence max per option. Pick in under 5 seconds.
-* After each review section, pause and ask for feedback before moving on.
+- Unresolved decisions: ___
 
 ## Review Log
 
@@ -1024,6 +1033,3 @@ Use AskUserQuestion with only the applicable options:
 - **A)** Run /plan-design-review (only if UI scope detected and no design review exists)
 - **B)** Run /plan-ceo-review (only if significant product change and no CEO review exists)
 - **C)** Ready to implement — run /ship when done
-
-## Unresolved decisions
-If the user does not respond to an AskUserQuestion or interrupts to move on, note which decisions were left unresolved. At the end of the review, list these as "Unresolved decisions that may bite you later" — never silently default to an option.

plan-eng-review/sections/review-sections.md.tmpl

@@ -6,6 +6,9 @@
 
 {{LEARNINGS_SEARCH}}
 
+## Retrospective learning
+Check the git log for this branch. If there are prior commits suggesting a previous review cycle (e.g., review-driven refactors, reverted changes), note what was changed and whether the current plan touches the same areas. Be more aggressive reviewing areas that were previously problematic.
+
 **Present complete remedies.** Before asking about one issue, include the
 validation and failure handling needed to make that remedy work in its options.
 Record the individually approved remedy in the plan. Later sections verify and
@@ -18,6 +21,12 @@ approve independent issues or new TODOs. Keep those approvals separate.
 
 {{CONFIDENCE_CALIBRATION}}
 
+## Formatting rules
+* NUMBER issues (1, 2, 3...) and LETTERS for options (A, B, C...).
+* Label with NUMBER + LETTER (e.g., "3A", "3B"). These issue IDs are separate from the preamble's `D<N>` question sequence; cite the issue ID in the question title.
+* Keep each option label to one sentence; include the preamble's full reasoning and pros/cons below it.
+* Follow the per-issue approval rule in **CRITICAL RULE — How to ask questions**: wait for each finding's answer; zero-finding sections proceed as specified there.
+
 ### 1. Architecture review
 Evaluate:
 * Overall system design and component boundaries.
@@ -88,8 +97,13 @@ Follow the AskUserQuestion format from the Preamble above. Additional rules for
 * **Coverage vs kind:** for every per-issue AskUserQuestion you raise in this review, decide whether the options differ in coverage or in kind. If coverage (e.g., more tests vs fewer, complete error handling vs happy-path-only, full edge-case coverage vs shortcut), include `Completeness: N/10` on each option. If kind (e.g., architectural choice between two different systems, posture-over-posture, A/B/C where each is a different kind of thing), skip the score and add one line: `Note: options differ in kind, not coverage — no completeness score.` Do NOT fabricate scores on kind-differentiated questions — filler scores are worse than no score.
 * **Zero findings:** if a section has zero findings, state "No issues, moving on" and proceed. Otherwise, use AskUserQuestion for each finding — a finding with an "obvious fix" is still a finding and still needs user approval before any change lands in the plan.
 
+## Unresolved decisions
+If the user does not respond to an AskUserQuestion or interrupts to move on, note which decisions were left unresolved. At the end of the review, list these as "Unresolved decisions that may bite you later" — never silently default to an option.
+
 ## Required outputs
 
+Write the narrative outputs below to the active plan file, or to the review response when no plan file is present. Display the Completion Summary to the user and write separately named artifacts to their specified paths. Update TODOS.md only through its individual approval step below.
+
 ### "NOT in scope" section
 Every plan review MUST produce a "NOT in scope" section listing work that was considered and explicitly deferred, with a one-line rationale for each item.
 
@@ -153,6 +167,9 @@ Format: `Lane A: step1 → step2 (sequential, shared models/)` / `Lane B: step3
 
 ### Completion summary
 At the end of the review, fill in and display this summary so the user can see all findings at a glance:
+
+"Lake Score" counts complete options chosen out of decisions that compared a complete option with a shortcut; use `N/A` when there were no such decisions.
+
 - Step 0: Scope Challenge — ___ (scope accepted as-is / scope reduced per recommendation)
 - Architecture Review: ___ issues found
 - Code Quality Review: ___ issues found
@@ -165,15 +182,7 @@ At the end of the review, fill in and display this summary so the user can see a
 - Outside voice: ran (codex/claude) / skipped
 - Parallelization: ___ lanes, ___ parallel / ___ sequential
 - Lake Score: X/Y recommendations chose complete option
-
-## Retrospective learning
-Check the git log for this branch. If there are prior commits suggesting a previous review cycle (e.g., review-driven refactors, reverted changes), note what was changed and whether the current plan touches the same areas. Be more aggressive reviewing areas that were previously problematic.
-
-## Formatting rules
-* NUMBER issues (1, 2, 3...) and LETTERS for options (A, B, C...).
-* Label with NUMBER + LETTER (e.g., "3A", "3B").
-* One sentence max per option. Pick in under 5 seconds.
-* After each review section, pause and ask for feedback before moving on.
+- Unresolved decisions: ___
 
 ## Review Log
 
@@ -233,6 +242,3 @@ Use AskUserQuestion with only the applicable options:
 - **A)** Run /plan-design-review (only if UI scope detected and no design review exists)
 - **B)** Run /plan-ceo-review (only if significant product change and no CEO review exists)
 - **C)** Ready to implement — run /ship when done
-
-## Unresolved decisions
-If the user does not respond to an AskUserQuestion or interrupts to move on, note which decisions were left unresolved. At the end of the review, list these as "Unresolved decisions that may bite you later" — never silently default to an option.

plan-tune/SKILL.md

@@ -247,6 +247,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -272,7 +273,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

qa-only/SKILL.md

@@ -237,6 +237,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -262,7 +263,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

qa/SKILL.md

@@ -243,6 +243,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -268,7 +269,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

retro/SKILL.md

@@ -257,6 +257,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -282,7 +283,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

review/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

scripts/resolvers/preamble/generate-context-recovery.ts

@@ -6,15 +6,16 @@ export function generateContextRecovery(ctx: TemplateContext): string {
   // Branch-form discipline (#2550/#1851): FILE-PATH positions use $BRANCH —
   // the canonical slug form the gstack-slug eval on the first line sets
   // (tr '/' '-' then tr -cd 'a-zA-Z0-9._-', matching what gstack-review-log
-  // WRITES). The timeline.jsonl greps keep raw $_BRANCH because the timeline
-  // writer (preamble's gstack-timeline-log call) stores the raw branch in the
-  // "branch" field — slugging the reader there would break matching.
+  // WRITES). Initialize raw $_BRANCH here: skill-start runs in a separate
+  // process. Keep the timeline writer's slash-preserving allowlist and fallback;
+  // using the filename slug in the "branch" field would break matching.
   return `## Context Recovery
 
 At session start or after compaction, recover recent project context.
 
 \`\`\`bash
 eval "$(${binDir}/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=\${_BRANCH:-unknown}
 _PROJ="\${GSTACK_HOME:-$HOME/.gstack}/projects/\${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -40,5 +41,5 @@ fi
 
 If artifacts are listed, read the newest useful one. If \`LAST_SESSION\` or \`LATEST_CHECKPOINT\` appears, give a 2-sentence welcome back summary. If \`RECENT_PATTERN\` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If \`ACTIVE DECISIONS\` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for \`${binDir}/gstack-decision-search\` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with \`${binDir}/gstack-decision-log\` (\`--supersede <id>\` for a reversal). Reliable and local; gbrain not required.`;
+**Cross-session decisions.** Honor listed \`ACTIVE DECISIONS\` and their rationale; do not silently re-litigate them, and announce planned reversals. Use \`${binDir}/gstack-decision-search\` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with \`${binDir}/gstack-decision-log\` (\`--supersede <id>\` for reversals). Reliable and local; gbrain not required.`;
 }

scripts/resolvers/testing.ts

@@ -420,7 +420,7 @@ The plan should be complete enough that when implementation begins, every test i
 After producing the coverage diagram, write a test plan artifact to the project directory so \`/qa\` and \`/qa-only\` can consume it as primary test input:
 
 \`\`\`bash
-eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG  # sets SLUG and BRANCH
 USER=$(whoami)
 DATETIME=$(date +%Y%m%d-%H%M%S)
 \`\`\`

setup-deploy/SKILL.md

@@ -238,6 +238,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -263,7 +264,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

setup-gbrain/SKILL.md

@@ -237,6 +237,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -262,7 +263,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

ship/SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

skillify/SKILL.md

@@ -236,6 +236,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -261,7 +262,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

spec/SKILL.md

@@ -237,6 +237,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -262,7 +263,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

sync-gbrain/SKILL.md

@@ -238,6 +238,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -263,7 +264,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

test/branch-slug-hygiene.test.ts

@@ -19,7 +19,7 @@
  * Reader-side fix folded from community PR #1851 by @harjothkhara.
  */
 import { describe, test, expect } from 'bun:test';
-import { execSync } from 'child_process';
+import { execSync, spawnSync } from 'child_process';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
@@ -130,7 +130,7 @@ describe('branch slug hygiene (#2550, #1851)', () => {
     );
   });
 
-  test('live round-trip: gstack-review-log writes, Context Recovery probe finds it (slash branch)', () => {
+  test('live round-trip: Context Recovery finds slugged reviews and raw timeline branches in a fresh shell', () => {
     const home = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-home-'));
     const repo = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-repo-'));
     try {
@@ -156,22 +156,56 @@ describe('branch slug hygiene (#2550, #1851)', () => {
       const proj = path.join(home, 'projects', slug);
       expect(fs.existsSync(path.join(proj, 'feat-slug-hygiene-reviews.jsonl'))).toBe(true);
 
-      // Reader: execute the rendered probe line with $BRANCH from gstack-slug.
+      // Reader: execute the complete rendered block without inheriting the
+      // external skill-start process's private shell variables.
       const ctx: TemplateContext = {
         skillName: 'test-skill', tmplPath: 'test.tmpl', host: 'claude',
-        paths: HOST_PATHS.claude, preambleTier: 2,
+        paths: { ...HOST_PATHS.claude, binDir: '"$TEST_BIN"' }, preambleTier: 2,
       };
-      const probeLine = generateContextRecovery(ctx)
-        .split('\n')
-        .find((l) => l.includes('-reviews.jsonl'))!;
-      const script = `_PROJ="${proj}"\nBRANCH="${branch}"\n${probeLine.trim()}`;
-      const out = execSync(`bash -c '${script.replace(/'/g, `'\\''`)}'`, {
-        cwd: repo, encoding: 'utf-8', timeout: 30_000,
-      });
-      expect(out).toContain('REVIEWS: 1 entries');
+      const script = generateContextRecovery(ctx).match(/```bash\n([\s\S]*?)\n```/)![1];
+      fs.writeFileSync(path.join(proj, 'timeline.jsonl'), [
+        { branch: 'feat/slug-hygiene', event: 'completed', skill: 'review' },
+        { branch: 'feat/slug-hygiene', event: 'started', skill: 'unfinished' },
+        { branch, event: 'completed', skill: 'slugged-decoy' },
+        { branch: 'stale/parent-branch', event: 'completed', skill: 'inherited-decoy' },
+        { branch: 'unknown', event: 'completed', skill: 'fallback' },
+        { branch: 'feat/slug-hygiene', event: 'completed', skill: 'ship' },
+      ].map(entry => JSON.stringify(entry)).join('\n') + '\n');
+      const recover = (cwd: string, inheritedBranch?: string) => {
+        const result = spawnSync('bash', ['-c', script], {
+          cwd, encoding: 'utf8', timeout: 30_000,
+          env: { ...env, GSTACK_PROJECT_SLUG: slug, TEST_BIN: path.join(ROOT, 'bin'), _BRANCH: inheritedBranch },
+        });
+        expect(result.status, result.stderr).toBe(0);
+        expect(result.stderr).not.toContain('not a git repository');
+        return result.stdout;
+      };
+      for (const inheritedBranch of [undefined, 'stale/parent-branch']) {
+        const out = recover(repo, inheritedBranch);
+        expect(out).toContain('REVIEWS: 1 entries');
+        expect(out.split('\n').filter(line => line.startsWith('LAST_SESSION:'))).toEqual([
+          'LAST_SESSION: {"branch":"feat/slug-hygiene","event":"completed","skill":"ship"}',
+        ]);
+        expect(out.split('\n').filter(line => line.startsWith('RECENT_PATTERN:'))).toEqual([
+          'RECENT_PATTERN: review,ship,',
+        ]);
+      }
 
       // Negative control: the raw-branch probe (the pre-fix shape) misses.
       expect(fs.existsSync(path.join(proj, 'feat/slug-hygiene-reviews.jsonl'))).toBe(false);
+
+      // Both an unnamed checkout and a non-repository use the same unknown
+      // timeline identity as skill-start/end, never an inherited branch.
+      execSync('git checkout -q --detach', { cwd: repo, timeout: 30_000 });
+      for (const cwd of [repo, home]) {
+        const out = recover(cwd, 'stale/parent-branch');
+        expect(out.split('\n').filter(line => line.startsWith('LAST_SESSION:'))).toEqual([
+          'LAST_SESSION: {"branch":"unknown","event":"completed","skill":"fallback"}',
+        ]);
+        expect(out.split('\n').filter(line => line.startsWith('RECENT_PATTERN:'))).toEqual([
+          'RECENT_PATTERN: fallback,',
+        ]);
+      }
     } finally {
       fs.rmSync(home, { recursive: true, force: true });
       fs.rmSync(repo, { recursive: true, force: true });

test/fixtures/golden/claude-ship-SKILL.md

@@ -239,6 +239,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -264,7 +265,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `~/.claude/skills/gstack/bin/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `~/.claude/skills/gstack/bin/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `~/.claude/skills/gstack/bin/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

test/fixtures/golden/codex-ship-SKILL.md

@@ -247,6 +247,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$($GSTACK_BIN/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -272,7 +273,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `$GSTACK_BIN/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `$GSTACK_BIN/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `$GSTACK_BIN/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `$GSTACK_BIN/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

test/fixtures/golden/factory-ship-SKILL.md

@@ -227,6 +227,7 @@ At session start or after compaction, recover recent project context.
 
 ```bash
 eval "$($GSTACK_BIN/gstack-slug 2>/dev/null)"
+_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-') || :; _BRANCH=${_BRANCH:-unknown}
 _PROJ="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
 if [ -d "$_PROJ" ]; then
   echo "--- RECENT ARTIFACTS ---"
@@ -252,7 +253,7 @@ fi
 
 If artifacts are listed, read the newest useful one. If `LAST_SESSION` or `LATEST_CHECKPOINT` appears, give a 2-sentence welcome back summary. If `RECENT_PATTERN` clearly implies a next skill, suggest it once.
 
-**Cross-session decisions.** If `ACTIVE DECISIONS` are listed, treat them as prior settled calls with their rationale — do not silently re-litigate them; if you're about to reverse one, say so explicitly. Reach for `$GSTACK_BIN/gstack-decision-search` whenever a question touches a past decision ("what did we decide / why / did we try"). When you or the user make a DURABLE decision (architecture, scope, tool/vendor choice, or a reversal) — NOT a turn-level or trivial choice — log it with `$GSTACK_BIN/gstack-decision-log` (`--supersede <id>` for a reversal). Reliable and local; gbrain not required.
+**Cross-session decisions.** Honor listed `ACTIVE DECISIONS` and their rationale; do not silently re-litigate them, and announce planned reversals. Use `$GSTACK_BIN/gstack-decision-search` for past-decision questions. Log DURABLE decisions by you or the user (architecture, scope, tool/vendor choice, reversal; not trivial or turn-level choices) with `$GSTACK_BIN/gstack-decision-log` (`--supersede <id>` for reversals). Reliable and local; gbrain not required.
 
 ## Writing Style (skip entirely if `EXPLAIN_LEVEL: terse` appears in the preamble echo OR the user's current message explicitly requests terse / no-explanations output)
 

test/skill-llm-eval.test.ts

@@ -680,7 +680,7 @@ describeIfSelected('Plan Review skill evals', [
       testName: 'plan-eng-review/SKILL.md sections',
       suite: 'Plan Review skill evals',
       skillPath: 'plan-eng-review/SKILL.md',
-      startMarker: '## BEFORE YOU START:',
+      startMarker: '# Plan Review Mode',
       endMarker: '## CRITICAL RULE',
       judgeContext: 'an engineering plan review framework with 4 review sections',
       judgeGoal: 'how to review a plan for architecture quality, code quality, test coverage, and performance — walking through each section interactively with AskUserQuestion',

test/workflow-judge-input.test.ts

@@ -187,6 +187,31 @@ describe('workflow judge file bundle', () => {
     }
   });
 
+  test('generated engineering review includes the scope choices and readiness probe its steps reference', () => {
+    const skillPath = 'plan-eng-review/SKILL.md';
+    const caller = readFileSync(join(ROOT, 'test/skill-llm-eval.test.ts'), 'utf8');
+    const markers = caller.match(/skillPath: 'plan-eng-review\/SKILL\.md',\s+startMarker: '([^']+)',\s+endMarker: '([^']+)'/);
+    expect(markers).not.toBeNull();
+    const [, startMarker, endMarker] = markers!;
+    const input = readWorkflowJudgeInput({ root: ROOT, skillPath, startMarker, endMarker });
+    const entrypoint = input.files.find(file => file.kind === 'entrypoint')!;
+    expect(entrypoint.content).toContain('B) A plan or design doc');
+    expect(entrypoint.content).toContain('## Scope gate');
+    expect(entrypoint.content.indexOf('## Scope gate')).toBeLessThan(entrypoint.content.indexOf('### Step 0: Scope Challenge'));
+    expect(entrypoint.content).toContain('## Web research runs in Aside');
+    expect(entrypoint.content).toContain('echo "READY: aside');
+    expect(entrypoint.content.indexOf('echo "READY: aside')).toBeLessThan(entrypoint.content.indexOf('4. **Search check:**'));
+    expect(occurrences(input.text, '## Scope gate')).toBe(1);
+    expect(occurrences(input.text, '### 1. Architecture review')).toBe(1);
+    const sections = input.files.filter(file => file.kind === 'section');
+    expect(sections.map(file => file.path)).toEqual(sectionPaths('plan-eng-review'));
+    for (const file of sections) {
+      const source = readFileSync(join(ROOT, file.path), 'utf8');
+      expect(file.content).toBe(source);
+      expect(occurrences(input.text, source)).toBe(1);
+    }
+  });
+
   test('generated plan-design passes retain their full section without duplicating Pass 1', () => {
     const input = readWorkflowJudgeInput({
       root: ROOT, skillPath: 'plan-design-review/SKILL.md', startMarker: '## Review Sections', endMarker: '## CRITICAL RULE',