v1.71.0.0 feat: token-load reduction — preamble runtime scripts, gated onboarding, 20 skill carves, CLAUDE.md trim (#2691)

* feat(gen): strip gen-time-only frontmatter keys from Claude renders interactive + benefits-from are read from the .tmpl by buildContext at generation time; no runtime, host, or test reader consumes them from the generated SKILL.md (e2e-harness-audit reads .tmpl; benefits-from tests assert rendered prose). gbrain: stays (bin/gstack-brain-context-load reads it from the installed render); hooks: stays (Claude Code host wires PreToolUse from it). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(gen): regenerate SKILL.md — dead frontmatter keys removed Mechanical regen after hosts/claude.ts stripFields change. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(test): context-budget ratchet — CI ceilings on always-on + eager token ledgers New free test grades the two ledgers nothing else guards: the full-frontmatter always-on catalog (aggregate) and per-skill eager tokens (SKILL.md + forced-read refs), via checkBudget from lib/context-bill.ts. Ceilings live in test/fixtures/context-budget.json with x1.05/x1.10 headroom; regenerate with bun test/helpers/capture-context-budget.ts. New skills fail until consciously budgeted; removed skills fail until the fixture is refreshed; reductions ratchet the ceilings down so wins lock in. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(todos): file output-template carve wave + plan-ceo doctrine revisit; mark preamble-carve P3 in flight Two follow-ups deferred from the approved token-reduction program (CEO review 'NOT in scope' list), filed with full context per TODOS format. The existing P3 preamble-carve entry gets a status update pointing at the program that supersedes it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): review findings — Windows path normalization, full totals rebuild, ratchet coverage Pre-landing review (5 specialists) found one critical: the ratchet test runs in the curated Windows lane, where path.relative yields backslash skill names that miss the test/ filter and mismatch every POSIX fixture key. Names are now normalized once in buildRatchetBill (toPosixName) and the fixture filter is tightened to test/fixtures/. All eight Bill.totals fields are rebuilt from the filtered list (no fixture-polluted perInvocation/totalMd numbers for future consumers). New coverage: Windows-separator normalization pins, a captureContextBudget round-trip against tree-a (headroom math exact), a stripFields regression pin (interactive/benefits-from absent from renders, hooks/gbrain preserved), and the ceilings test no longer double-reports stale-fixture entries. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): adversarial findings — stable root key, symlink-alias dedupe, fixture-shape guard Adversarial review (Claude subagent) verified the fixture's root-skill key was the capture machine's checkout dirname: any non-gstack-named clone (every Conductor worktree) failed the free suite, and the documented re-run-the-capture recovery baked the local dirname into the committed fixture — silent corruption through the tool's own protocol. The root skill is now pinned to ROOT_SKILL_KEY ('gstack', its frontmatter name). Symlink aliases are realpath-deduped (census precedent): connect-chrome no longer gets its own ceiling, so Windows checkouts that materialize the symlink as a plain file can't fail the stale-ceiling set-equality test. New guards: fixture-shape validation (a string alwaysOnTotal can no longer silently disable the ceiling), a mutation pin that the filter shrinks the always-on ledger vs the raw bill, an alwaysOnTotal violation test (the branch was load-bearing with only under-budget coverage), and an atomic temp+rename fixture write. Fixture regenerated: 59 ceilings, alwaysOnTotal 6344. Deferred with a TODO: anchoring transformFrontmatter's denylist strip to the frontmatter block (latent, zero live collisions, pre-existing path). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump version and changelog (v1.69.1.0) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: update project documentation for v1.69.1.0 CLAUDE.md: Token ceiling section documents the context-budget ratchet as the third guard (test file, fixture, new-skill budgeting, capture command). CONTRIBUTING.md: Tier 1 guard list gains a Context-budget ratchet bullet; the Adding-a-new-skill checklist gains the budget-capture step. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: pin exact guard semantics for the context-budget ratchet in CLAUDE.md Doc-review finding: "a third enforced ceiling" undercounted the guard family (skill-size-budget floors and parity ratios also watch these ledgers, relatively). Rephrased to match the ratchet test's own header: absolute ceilings vs relative floors/ratios. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(changelog): heaviest-skill claim matches the fixture (land-and-deploy edges review by 0.2%) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(bin): gstack-skill-start + gstack-skill-end — the preamble runtime, consolidated Absorbs the ~13KB of bash every tier-2+ SKILL.md inlined twice over (bootstrap fence + artifacts-sync fence) and the skill-end telemetry/sync fences. Same KEY: value STATUS-line contract the prose interprets, plus SKILL_START_PROTO handshake (OV5), SESSION_ID/TEL_START echoes, GSTACK_HOME-normalized state paths (EOV7), --parent-pid session identity (EOV5: $PPID inside the script is the ephemeral tool-call shell), OV4 sanitization of passthrough output, and a receipted daily artifacts pull (_receipted_git, brain-sync class, fail-closed). Per-line || true error style throughout (F3) — a mid-script failure never drops later STATUS lines. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(gen): preamble resolvers emit a script invocation fence instead of inline bash generate-preamble-bash: ~6.3KB fence -> 4-line gstack-skill-start invocation (quoted-tilde pitfall handled: leading ~ interpolates through $HOME; env-var hosts keep $GSTACK_BIN) + degraded-mode prose (F1/EOV8: safe defaults, consent gates deferred-never-lost; OV5: proto rule). generate-brain-sync-block: ~6.8KB bash -> interpretation prose + the privacy stop-gate (stays inline until Phase 2's gated emission). generate-completion-status: telemetry fence -> one gstack-skill-end call with SESSION_ID/TEL_START handoff. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(gen): regenerate all skills + golden fixtures — inline preamble bash removed Mechanical regen after the resolver change: −12,628 lines across 52 renders (corpus 952K -> 806K render tokens; tier-2 skills −11-13KB each). Golden per-host ship fixtures refreshed from the fresh claude/codex/factory renders. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: skill-start contract suite + preamble A/B eval + touchfiles registration test/gstack-skill-start.test.ts (11 free tests): STATUS-key contract vs the prose (F2), per-host fence resolution shapes (E1), proto-first, OV4 marker sanitization, --parent-pid identity, headless suppression, skill-end duration math + pending cleanup. test/skill-e2e-preamble-script-ab.test.ts (gate tier, OV7): inline-bash render (pinned from 29785978) vs script render with the fence redirected at the worktree bin (EOV2 — hermetic evals otherwise resolve the operator install and silently exercise degraded mode). 21 touchfiles dep lists gain the two bin scripts (EOV9) so future script edits select the preamble evals; selection-count pin updated 23->24. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: repin ~70 assertions to the script contract — every literal gets a successor Assertions that pinned inline-bash internals (update-check guard, _SESSIONS reaping, telemetry start/end blocks, routing probe, repo-strip producer, first-task gating, EXPLAIN_LEVEL/QUESTION_TUNING echoes, #2499 jq scope resolution, Issue-8 CONDUCTOR gate) now pin the same invariants in their new home: bin/gstack-skill-start / bin/gstack-skill-end file content for script internals, the invocation fence + interpretation prose for render-side behavior. No assertion deleted without a successor; live-execution tests (routing probe, brain-sync jq) run against script bytes unchanged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(test): re-baseline size floors + ratchet ceilings down (EOV1/OV9 protocol) parity-baseline-v1.69.1.0.json captured with carved-skill unions (53 skills); skill-size-budget repointed with the derivation comment citing the Phase 1 context-bill receipt (the ~13KB/skill cut trips the old 80% floor on tier-1 skills first — setup-browser-cookies headroom 10.8KB < the cut). The v1.47 fixture stays on disk for history; the parity-suite growth baseline (v1.64.1.0) is untouched. Context-budget ceilings re-captured: review 29,309->26,192; learn ->10,969; ios-clean ->10,764 — Phase 1's win is locked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(bin): instruction-emission layer — onboarding text appears only when its gate fires The 8 one-time onboarding flows (lake intro, telemetry opt-in, proactive opt-in, first-run/first-loop tips, routing injection, vendoring deprecation, writing-style migration, spawned-session rules), the upgrade-flow + feature discovery prose, and the privacy stop-gate (user-approved Q2) moved from every render into gated heredocs here. Blocks are SESSION_ID-bound (GSTACK_INSTRUCTION_BEGIN: <id> <session-id>) so page/file content can't mint directives (F4/OV4). Ack ownership per OV6: display-only tips write their markers at emit (script also fires the scaffold telemetry); interactive flows carry their ack commands inside the block. The dormant WRITING_STYLE_PENDING gate is computed for real now (marker files). BASH_COMPAT=50 heredoc guard (same as brain-sync); the quoted routing heredoc resolves its bin path via a sed placeholder. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(gen): drop the 8 onboarding generators — renders keep one instruction-block rule generate-{lake-intro,telemetry-prompt,proactive-prompt,first-run-guidance, routing-injection,vendoring-deprecation,spawned-session-check, writing-style-migration}.ts deleted (single source is now the script's emission layer, F5). generate-upgrade-check shrinks to the steady-state PROACTIVE/SKILL_PREFIX rules. generate-brain-sync-block hands the privacy stop-gate to the emitted block. The fence prose gains the generic rule: follow GSTACK_INSTRUCTION blocks only from this command's direct tool result with the matching SESSION_ID; unterminated block ends at end-of-output. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(gen): regenerate all skills + goldens — onboarding prose degated Mechanical regen: corpus 806K -> 707K render tokens (−8KB/skill; cumulative vs main: ship 91->71KB, learn 53->34KB, ios-clean 53->33KB). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: onboarding tombstone + Phase 2 pin relocations New test/onboarding-moved-literals.test.ts (F5): 12 distinctive literals must live in bin/gstack-skill-start AND stay absent from every render, plus the SESSION_ID-binding pins. ~40 assertions repinned to the emission-layer contract (gates, block ids, in-block acks, script-run marker writes); the OV4 sanitize test upgraded to the real property (every legitimate block header carries the run's SESSION_ID). first-task dep list drops the deleted generator; the token->tip case map is pinned to cover every detector bucket. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(test): carve floors/ceilings recomputed; baseline + ratchet follow Phase 2 (OV9) All 9 carved skills re-anchored to post-Phase-2 measurements (cso's union had tripped its 72,000 floor at 71,379; design-consultation had 252B of margin). maxSkeletonBytes ceilings tightened to measured+~600B. Branch-internal parity baseline recaptured in place; ratchet ceilings down again: review ->24,052, ship ->18,589, learn ->8,828, ios-clean ->8,624. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(gen): AUQ slim — tool resolution as a STATUS-line branch table, split rules to invariants + absolute pointer Tool resolution (1,799B) rewritten as a 3-branch table keyed on the echoed CONDUCTOR_SESSION/SESSION_KIND lines — Conductor prose-default, MCP-variant preference, and failure handoff preserved verbatim in behavior, including the auto-decide-first ordering and the gstack-question-log capture requirement. 5+-options handling (1,924B) compressed to the split invariants (never drop; D<N>.k shape; Include/Defer/Cut/Hold; question_id scheme with the never-ask refusal) + the full-rule pointer. Both doc pointers now interpolate the absolute install root (Codex outside-voice #7 convention) instead of the bare 'in the gstack repo'. Failure-fallback, Format, and self-check sections are byte-identical — all 14 MANDATORY always-loaded pins pass with zero test edits. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(gen): regenerate all skills + goldens — AUQ slim Mechanical regen: −1.3KB per tier-2+ skill (ship 69.9KB, learn 32.5KB). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(test): baseline + ratchet follow Phase 3 (OV9); OV8 evaluated — shrink floor stays Branch-internal baseline recaptured; ratchet ceilings down again. OV8's floor-retirement question, evaluated as planned after Phase 3: the 80% shrink floor stays — it uniquely catches accidental body deletion in non-carved skills BETWEEN ratchet recaptures, and the capture command has amortized the fixture-refresh cost that motivated retiring it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(review): carve adversarial, plan-completion, and review-army into sections The three resolver macros ship already carves as siblings now load on demand for /review too: skeleton 100.2KB -> 55.0KB (-45%), union 93.4KB. Resolvers stay the single source of truth (sections wrap the macros). Step 0/1, scope drift, critical pass, confidence calibration, and fix-first stay always-loaded. Fixtures and pins follow the moved content (codex-hardening wrapped-sites, review-army E2E fixture builds skeleton+sections with an empty-fixture guard). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(codex): carve the three mutually exclusive modes into sections Review/Challenge/Consult mode bodies (34.7KB where at most one ever runs) load on demand: skeleton 81.0KB -> 55.2KB, union 1.04x the monolith. The mode dispatch, filesystem boundary, and a new always-loaded 'Synthesis recommendation (REQUIRED) — all modes' block stay skeleton-side (the AUQ per-skill pins pass unchanged); the plan-file report + exit gate render after the last section pointer per the gateAfterStop pattern. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(land-and-deploy): carve first-run validation, readiness gate, and merge/deploy into sections The once-per-repo dry-run validation, the pre-merge readiness gate, and the merge + deploy-strategy steps (37.8KB) load on demand: skeleton 91.1KB -> 55.7KB. Step 1.5 keeps its detection bash as the dispatch; the first-run section's fingerprint-save block gained {{SLUG_EVAL}} so it is self-contained. Zero content lost (line-coverage checked against HEAD). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(ios): demote the four ios skills to preamble-tier 2 (Phase 5) They never consume the tier-3 sections (repo-mode ownership, search-before- building) but do fire AskUserQuestion, which tier >=2 provides — verified by grep before the plan review. -2.2KB per skill. Render assertions pin the demotion (tier-3 sections absent, AUQ format present). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(guards): register wave-1 carves; monolith invariants retire; baselines + ratchet follow CARVE_GUARDS gains review/codex/land-and-deploy (12 carved skills total); their MONOLITH_INVARIANTS entries retire (invariants now generate from the registry, cso precedent). Touchfiles: carve-section-loading covers the three new carves; the codex + land-and-deploy LLM-judge dep lists widen to their sections. Regen + goldens + branch-internal baseline + ratchet ceilings recaptured (review 24,052 -> skeleton-based ceiling; union floors hold). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(gen-skill-docs): review render pins read the carved union The review carve's readSkillUnion conversions (same pattern its neighbor carved-skill pins already use). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(autoplan): carve the four review phases + tasks aggregator into sections Phase bodies (CEO/Design/Eng/DX consensus flows) and the Implementation Tasks aggregator load on demand; Design and DX stay separate sections because each is independently conditional on scope. Skeleton 83.7KB -> 58.7KB (-30% always-loaded); the 6 decision principles, classification, sequencing, and explicit skip-condition dispatch stay always-loaded. The chain E2E's phase-complete markers now live only in sections, so its assertions double as section-read proof (behavioral: external). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(spec): carve the post-confirmation gate-and-file tail into one section Phases 1-4 are the turn-1 conversational spine — carving them would force the Read on the first user message for zero real savings. The mechanical tail (4.5/4.5a/4.5b redaction gates + Phase 5 filing + TTHW telemetry) fires only after draft confirmation: a genuine lazy boundary, kept as ONE section so the gh-issue-create bash can never load without the fail-closed redaction gate that precedes it. Skeleton 65.4KB -> 50.7KB; all ~85 phase-structure invariants migrated location-aware plus a new carve-shape suite (56 tests). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(setup-gbrain): carve the branch-exclusive install paths into sections Brain-init (Paths 1/2/3/4 bodies), engine remediation, transcript gate, and CLAUDE.md persist load on demand — at most one install route ever runs. Skeleton 75.3KB -> 57.0KB; the Step 1 detect and Step 2 path dispatch stay always-loaded. New buildSetupGbrainFixture helper gives the periodic E2Es extract-don't-copy fixtures with a non-empty guard; the voyage-code-3 gate counts scan the tmpl union (the third init site lives in engine-remediation). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore(guards): register wave-2 carves (15 carved skills); autoplan monolith retires; baselines follow CARVE_GUARDS gains autoplan (behavioral: external via the chain eval), spec, and setup-gbrain; autoplan's MONOLITH_INVARIANTS entry retires. Touchfiles: setup-gbrain periodic dep lists gain the section tmpls + fixture helper; the stale-brain-refs scan covers setup-gbrain/sections. Regen + goldens + branch baseline + ratchet recaptured. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(qa): carve QA patterns + health rubric into on-demand sections (68→48KB skeleton) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(browse): carve full command list + snapshot flags into sections/command-list.md (39→27KB skeleton) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(retro): absorb inline git/awk metrics into bin/gstack-retro-metrics + carve report format RETRO_METRICS_PROTO: 1 contract, local git reads only (fetch stays in the skill prose), degraded path documented in the skeleton. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: register wave-3 carves (qa, browse, retro) — guards, touchfiles, pins, baselines CARVE_GUARDS gains the three entries; qa's monolith invariant retires. auq-format carve-safety now keys on the skeleton+sections union shipping the AUQ block (first tier-1 carve: browse never renders it by design). Baselines: parity v1.69.1.0 at 18 sectioned skills; ratchet recaptured. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): drop stale generate-lake-intro import (generator deleted in the emission-layer move) Sol scope discipline stays pinned via the model overlay + completeness section; the lake intro is now a single script-emitted blurb. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(office-hours): carve Phase 2A/2B into mode-exclusive sections (81→67KB skeleton) A session runs exactly one mode, so a builder session never loads the 13KB startup diagnostic. Mode mapping and the vibe-shift upgrade rule stay in the skeleton. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(design): carve UX doctrine + Pretext patterns into read-on-demand sections design-html 57→49KB, design-shotgun 53→50KB. Sections wrap {{UX_PRINCIPLES}} so scripts/resolvers/design.ts stays the source of truth; the pretext-patterns STOP sits at the top of Step 3 so the read provably precedes the Write. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: register wave-4 carves (office-hours ext, design-html, design-shotgun) — 20 carved skills Both design entries carry requiredReads + loading-eval scenarios (D3A condition). office-hours phase sections are mode-exclusive, so only the always-reached design/handoff section is a deterministic requiredRead. Baselines and ratchet recaptured. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: trim CLAUDE.md 66.4→44.9KB — verbatim moves to docs/, pointers stay inline Moved: browser/sidebar/server internals, CHANGELOG release-summary format spec, project tree, hermetic-E2E detail, slop-scan reference, OpenClaw publishing. Kept inline: every hard behavioral rule (dist/ ban, redaction scan-at-sink, egress receipts, bisect commits, eval detach, CHANGELOG entry rules), the machine-managed GBrain block (byte-identical), and the '## Deploying to the active skill' header with gbrain-refresh in range (pinned by test/gbrain-refresh-install-render.test.ts). No voice rewrites. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): seed onboarding markers into the hermetic child GSTACK_HOME EOV7 made bin/gstack-skill-start honor GSTACK_HOME, so the operator-HOME seeding in e2e-helpers.ts no longer reaches hermetic children — the emission layer fired lake-intro/telemetry prompts that burned turns and stalled PTY tests waiting on an answer (observed: plan-mode-no-op derailed by the telemetry question). Onboarding-specific tests pin their own GSTACK_HOME per-test, which merges over this seed. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: raise carve-section-loading wall clock to 480s SDK / 540s bun The heavy full-workflow scenarios satisfy their required section reads inside 60s but need 300-450s to finish the report on slower sandboxes; the 300s default read as a loading failure when the carve invariant held (traces: plan-eng-review read its section at 8s, office-hours all three at 24s, design-html both at 50s — all timed out mid-report). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(security): harden the skill-start trust boundary — review-army findings Session ID gains a urandom suffix (block binding unforgeable by reflected content); _sanitize also neutralizes spoofed SESSION_ID: lines; branch names are charset-clamped before JSON embedding (skill-start + skill-end); .brain-last-push reads first line only with a charset clamp; the artifacts URL echo routes through _sanitize; the privacy consent gate fires in interactive sessions only (spawned auto-choose could accept consent no human gave — emission order is not a safety property); the daily pull gets non-interactive + slow-network git guards and stamps only when the receipted path ran; ~/.claude.json gets a grep pre-filter before the jq parse. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(resolvers): question-log session_id becomes a substitution placeholder + stale-comment sweep The question-log block bound $_SESSION_ID, a shell variable the consolidated fence never sets — hook-less hosts logged empty session_id, breaking /plan-tune per-session grouping. It now uses the same substitute-from-the-skill-start-echoes contract as the telemetry block. Also: retired the pre-Phase-2 stop-gate docstring, repointed the gbrain-local-status cross-reference at the script's inline jq, dropped an orphaned section comment, documented retro-metrics' suffix-only census. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: regenerate renders for the question-log placeholder; goldens + baselines follow Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: hermetic update-check, onboarding gate sequencing, seeding parity The contract test's child did a live git ls-remote + curl to github.com on every bun run test (update_check config now gates it off); the headless test gets a fresh GSTACK_HOME so the suppression is actually exercised; a new OV6 test drives the script three times to pin ack-at-emit and gate sequencing; hermetic seeding covers the config-keyed privacy gate; the EVALS_HERMETIC=0 debug seeding reaches marker parity. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(ci): demote the preamble A/B to periodic (OV7) and add it to the periodic matrix Post-Phase-3 demotion per the plan; the eval needs fetch-depth 0 (it git shows a pre-Phase-1 sha), which only the periodic workflow provides — and a static matrix entry so it can't silently never run. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump version and changelog (v1.70.0.0) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: update project documentation for v1.70.0.0 ARCHITECTURE.md: the preamble section now describes the v1.70 runtime — the rendered {{PREAMBLE}} block invokes bin/gstack-skill-start and reads STATUS lines, gstack-skill-end logs telemetry, and one-time onboarding text arrives as gated GSTACK_INSTRUCTION blocks instead of riding in every render. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: doc-review fixes — repair moved-file links, drop unbacked session-count claim docs/BROWSER_INTERNALS.md: the two ARCHITECTURE.md anchor links broke when the section moved from repo-root CLAUDE.md into docs/ — now ../ARCHITECTURE.md. ARCHITECTURE.md: the preamble's session-tracking item claimed an active-session count and an "ELI16 mode" that no shipped code implements (the count computation was deleted with the inline preamble); describe the real touch-and-prune behavior instead. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(changelog): correct numeric claims against measured counts 50 of 62 installed skills dropped (fixture/alias entries have no preamble); 11 new carves + a deeper office-hours carve = 9→20; test counts match the files (13 / 11 / 3 / 7). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: repoint the preamble-runtime version reference after the queue rebump (v1.71.0.0) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(e2e-design): widen the Aesthetic synonym set — vocabulary variance, not a regression Both attempts in run 33090283032 produced judge-praised DESIGN.md files phrased as 'design principles'/'design language' without any of the four original literals; inputs were identical to the prior passing run 32899975845 (design-consultation untouched by the intervening merge). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(test): stage design-consultation's sections/ into the E2E fixture The skill has been carved since v1.57.0.0 — the DESIGN.md structure prescription (the AESTHETIC proposal template) lives in sections/proposal-and-preview.md behind a STOP-read. The fixture only copied SKILL.md, so the agent improvised structure from the skeleton and the section-synonym check has been a coin flip since the carve (CI run 33090283032 trace shows 'no sections dir'; the local eval store has the same failure on 2026-08-25 while that day's CI run passed on lucky vocabulary). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-29 17:30:40 +02:00 · 2026-08-27 09:50:31 -07:00
parent a3749bfa4b
commit 394db326f2
227 changed files with 16814 additions and 34123 deletions
@@ -0,0 +1,360 @@
+#!/usr/bin/env bash
+# gstack-retro-metrics — /retro's metric pipelines, consolidated (token-reduction).
+#
+# Absorbs the inline git/awk pipelines retro/SKILL.md used to carry in Steps
+# 0.5-9 and 11 (~13KB of fences in every install). The skill now runs ONE
+# fence; this script emits labeled `METRIC_NAME: value` lines the prose
+# interprets. The contract is pinned by test/gstack-retro-metrics.test.ts.
+#
+# LOCAL READS ONLY — no network ops of any kind. The freshness fetch stays in
+# the skill's own Step 0.5 fence (skill prose, same as before this script
+# existed), so this script never needs egress receipts.
+#
+# Conventions mirror bin/gstack-skill-start:
+#   - Paths resolve $0-relative (works for every host + install layout).
+#   - State paths honor ${GSTACK_HOME:-$HOME/.gstack}.
+#   - Error style: per-line `|| true`, never `set -e` — a mid-script failure
+#     must not drop later METRIC lines.
+#   - No heredocs (nothing to BASH_COMPAT-guard; see
+#     test/heredoc-pipe-deadlock.test.ts if one is ever added).
+#
+# Usage:
+#   gstack-retro-metrics --base <default-branch> --since <git-since-expr> \
+#                        [--until <git-until-expr>]
+#
+#   --base   the detected default branch (from BASE_BRANCH_DETECT). The script
+#            prefers origin/<base>, falls back to the local <base> (local-only
+#            repos), then HEAD. The ref actually used is echoed as RETRO_REF.
+#   --since  midnight-aligned ISO date ("2026-03-11T00:00:00") or a relative
+#            expression ("24 hours ago"). Default: "7 days ago".
+#   --until  optional window end (compare mode's prior window).
+
+BASE=""
+SINCE="7 days ago"
+UNTIL=""
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --base)  BASE="$2"; shift 2 ;;
+    --since) SINCE="$2"; shift 2 ;;
+    --until) UNTIL="$2"; shift 2 ;;
+    *) shift ;;
+  esac
+done
+
+# $0-relative resolution (parity with gstack-skill-start; any future
+# sibling-bin call must go through $_BIN, never bare PATH lookup).
+_SCRIPT_DIR=$(cd "$(dirname "$0")" 2>/dev/null && pwd)
+_BIN="$_SCRIPT_DIR"
+_GH="${GSTACK_HOME:-$HOME/.gstack}"
+
+echo "RETRO_METRICS_PROTO: 1"
+
+if ! git rev-parse --git-dir >/dev/null 2>&1; then
+  echo "RETRO_METRICS_ERROR: not inside a git repository"
+  exit 0
+fi
+
+# ── Guard + ref resolution (Step 0.5's local checks; the fetch stays in prose) ─
+_HAS_ORIGIN=$(git remote 2>/dev/null | grep -c '^origin$' || true)
+case "$_HAS_ORIGIN" in ''|*[!0-9]*) _HAS_ORIGIN=0 ;; esac
+[ "$_HAS_ORIGIN" -gt 0 ] && echo "GUARD_REMOTE: origin" || echo "GUARD_REMOTE: none"
+
+_HEAD_REF=$(git symbolic-ref --quiet --short HEAD 2>/dev/null || true)
+[ -n "$_HEAD_REF" ] && echo "GUARD_HEAD: $_HEAD_REF" || echo "GUARD_HEAD: detached"
+
+if [ -z "$BASE" ]; then
+  BASE=$(git symbolic-ref --quiet refs/remotes/origin/HEAD 2>/dev/null | sed 's|^refs/remotes/origin/||')
+fi
+if [ -z "$BASE" ]; then
+  for _CAND in main master; do
+    if git rev-parse --verify --quiet "refs/heads/$_CAND" >/dev/null 2>&1 \
+       || git rev-parse --verify --quiet "refs/remotes/origin/$_CAND" >/dev/null 2>&1; then
+      BASE="$_CAND"; break
+    fi
+  done
+fi
+[ -n "$BASE" ] || BASE="$_HEAD_REF"
+
+REF="HEAD"
+if [ -n "$BASE" ] && git rev-parse --verify --quiet "refs/remotes/origin/$BASE" >/dev/null 2>&1; then
+  REF="origin/$BASE"
+elif [ -n "$BASE" ] && git rev-parse --verify --quiet "refs/heads/$BASE" >/dev/null 2>&1; then
+  REF="$BASE"
+fi
+echo "RETRO_REF: $REF"
+
+_LATEST=$(git log -1 --format=%ci "$REF" 2>/dev/null | cut -d' ' -f1)
+echo "GUARD_LATEST_COMMIT: ${_LATEST:-unknown}"
+
+echo "WINDOW_SINCE: $SINCE"
+echo "WINDOW_UNTIL: ${UNTIL:-(now)}"
+
+_USER_NAME=$(git config user.name 2>/dev/null || true)
+_USER_EMAIL=$(git config user.email 2>/dev/null || true)
+echo "USER_NAME: ${_USER_NAME:-unknown}"
+echo "USER_EMAIL: ${_USER_EMAIL:-unknown}"
+
+# Window args, applied uniformly to every windowed git query below.
+_S="--since=$SINCE"
+_U=""
+[ -n "$UNTIL" ] && _U="--until=$UNTIL"
+
+# ── Main pass: one numstat walk computes the whole per-commit metric family ──
+# Emits COMMIT: lines (newest first, capped) plus every aggregate. Subjects may
+# contain '|', so fields are re-joined from index 6 on. Test-file detection is
+# the union of the historical patterns (dir-based test/|spec/|__tests__/ and
+# suffix-based .test./.spec./_test./_spec.).
+git log "$REF" "$_S" ${_U:+"$_U"} --date=format-local:'%Y-%m-%d %H:%M' \
+    --format='C|%h|%aN|%at|%ad|%s' --numstat 2>/dev/null | awk '
+  function is_test(p) {
+    return (p ~ /(^|\/)(tests?|spec|__tests__)\//) || (p ~ /(\.(test|spec)\.|_test\.|_spec\.)/)
+  }
+  function type_of(s) {
+    if (s ~ /^Merge /) return "merge"
+    sub(/^v[0-9][0-9.]* /, "", s)   # squash-merge convention: "v1.2.3.0 fix: ..."
+    if (match(s, /^(feat|fix|refactor|test|chore|docs|perf|style|build|ci|revert)(\(|!|:)/)) {
+      t = substr(s, 1, RLENGTH - 1); sub(/[(!:]$/, "", t); return t
+    }
+    return "other"
+  }
+  function bucket_of(loc) {
+    if (loc < 100) return "small"; if (loc < 500) return "medium"
+    if (loc < 1500) return "large"; return "xl"
+  }
+  function flush() {
+    if (h == "") return
+    commits++
+    ins += cins; del += cdel; tins += ctins
+    files_sum = (cfiles > 20 ? 20 : cfiles); weighted += files_sum
+    t = type_of(subj); types[t]++; atypes[author "|" t]++
+    if (t == "merge") merges++
+    hour = substr(dt, 12, 2); hours[hour]++; ahours[author "|" hour]++
+    day = substr(dt, 1, 10); days[day] = 1
+    wk = int((anchor - at) / 604800)
+    wcommits[wk]++; wins[wk] += cins; wdel[wk] += cdel; wtins[wk] += ctins
+    if (wk > maxwk) maxwk = wk
+    acommits[author]++; ains[author] += cins; adel[author] += cdel; atins[author] += ctins
+    loc = cins + cdel; sizes[bucket_of(loc)]++
+    if (loc > bigloc) { bigloc = loc; bigline = h "|" loc "|" author "|" subj }
+    if (loc > abigloc[author]) { abigloc[author] = loc; abig[author] = h "|" loc "|" subj }
+    # 45-minute session gaps (walked newest→oldest; equivalent to ascending).
+    if (prev_at == 0) { sess = 1; sess_end = at; }
+    else if (prev_at - at > 2700) {
+      sess_dur = (sess_end - sess_start_at) / 60; classify(sess_dur)
+      sess++; sess_end = at
+    }
+    sess_start_at = at; prev_at = at
+    if (commits <= 300) printf "COMMIT: %s|%s|%s|+%d/-%d|%s\n", h, author, dt, cins, cdel, subj
+    h = ""
+  }
+  function classify(mins) {
+    total_mins += mins
+    if (mins >= 50) deep++; else if (mins >= 20) medium++; else micro++
+  }
+  /^C\|/ {
+    flush()
+    n = split($0, a, "|")
+    h = a[2]; author = a[3]; at = a[4] + 0; dt = a[5]
+    subj = a[6]; for (i = 7; i <= n; i++) subj = subj "|" a[i]
+    if (anchor == 0) anchor = at
+    cins = 0; cdel = 0; ctins = 0; cfiles = 0
+    next
+  }
+  /^[0-9-]+\t/ {
+    if ($1 != "-") cins += $1; if ($2 != "-") cdel += $2
+    if ($1 != "-" && is_test($3)) ctins += $1
+    cfiles++
+    filecount[$3]++
+    d = ($3 ~ /\//) ? substr($3, 1, index($3, "/") - 1) "/" : "(root)"
+    dircount[d]++; adir[author "|" d]++
+    if ($3 ~ /(\.(test|spec)\.|_test\.|_spec\.)/) testfiles[$3] = 1
+  }
+  END {
+    flush()
+    if (commits > 0 && prev_at != 0) { sess_dur = (sess_end - sess_start_at) / 60; classify(sess_dur) }
+    if (commits > 300) printf "COMMIT_LIST_TRUNCATED: showing 300 of %d (newest first; git log for the rest)\n", commits
+    printf "COMMITS: %d\n", commits
+    printf "MERGE_COMMITS: %d\n", merges
+    nauth = 0; for (au in acommits) nauth++
+    printf "CONTRIBUTORS: %d\n", nauth
+    printf "INSERTIONS: %d\n", ins
+    printf "DELETIONS: %d\n", del
+    printf "NET_LOC: %d\n", ins - del
+    printf "TEST_INSERTIONS: %d\n", tins
+    printf "TEST_RATIO: %s\n", (ins > 0 ? sprintf("%d%%", tins * 100 / ins) : "n/a")
+    printf "WEIGHTED_COMMITS: %d\n", weighted
+    nd = 0; for (d in days) nd++
+    printf "ACTIVE_DAYS: %d\n", nd
+    ntf = 0; for (f in testfiles) ntf++
+    printf "TEST_FILES_CHANGED: %d\n", ntf
+    printf "SESSIONS: %d\n", sess
+    printf "DEEP_SESSIONS: %d\n", deep
+    printf "MEDIUM_SESSIONS: %d\n", medium
+    printf "MICRO_SESSIONS: %d\n", micro
+    printf "TOTAL_ACTIVE_MINUTES: %d\n", total_mins
+    printf "AVG_SESSION_MINUTES: %d\n", (sess > 0 ? total_mins / sess : 0)
+    if (total_mins >= 5) printf "LOC_PER_SESSION_HOUR: %d\n", int(ins / (total_mins / 60) / 50 + 0.5) * 50
+    else printf "LOC_PER_SESSION_HOUR: n/a (too little session time)\n"
+    line = ""
+    for (t in types) line = line (line == "" ? "" : " ") t "=" types[t]
+    printf "COMMIT_TYPES: %s\n", (line == "" ? "none" : line)
+    printf "FIX_RATIO: %s\n", (commits > 0 ? sprintf("%d%%", types["fix"] * 100 / commits) : "n/a")
+    printf "COMMIT_SIZE_BUCKETS: small=%d medium=%d large=%d xl=%d\n", sizes["small"], sizes["medium"], sizes["large"], sizes["xl"]
+    # Hour histogram (nonzero hours only, chronological).
+    line = ""
+    for (i = 0; i < 24; i++) { hh = sprintf("%02d", i); if (hours[hh] > 0) line = line (line == "" ? "" : " ") hh "=" hours[hh] }
+    printf "HOURS: %s\n", (line == "" ? "none" : line)
+    peak = ""; pc = -1
+    for (hh in hours) if (hours[hh] > pc) { pc = hours[hh]; peak = hh }
+    printf "PEAK_HOUR: %s\n", (peak == "" ? "n/a" : peak)
+    # Focus score: share of file changes in the single busiest top-level dir.
+    tot = 0; for (d in dircount) tot += dircount[d]
+    fd = ""; fc = -1
+    for (d in dircount) if (dircount[d] > fc) { fc = dircount[d]; fd = d }
+    if (tot > 0) printf "FOCUS_SCORE: %d%% (%s)\n", fc * 100 / tot, fd
+    else printf "FOCUS_SCORE: n/a\n"
+    if (bigline != "") printf "BIGGEST_COMMIT: %s\n", bigline
+    # Top-10 hotspots by change count.
+    for (k = 0; k < 10; k++) {
+      bf = ""; bc = 0
+      for (f in filecount) if (filecount[f] > bc) { bc = filecount[f]; bf = f }
+      if (bf == "") break
+      printf "HOTSPOT: %d %s\n", bc, bf
+      delete filecount[bf]
+    }
+    # Per-author lines, sorted by commits desc (selection sort — small n).
+    while (1) {
+      ba = ""; bc = -1
+      for (au in acommits) if (!(au in done) && acommits[au] > bc) { bc = acommits[au]; ba = au }
+      if (ba == "") break
+      done[ba] = 1
+      tr = (ains[ba] > 0 ? sprintf("%d%%", atins[ba] * 100 / ains[ba]) : "n/a")
+      # top-3 areas for this author
+      areas = ""
+      for (k = 0; k < 3; k++) {
+        bd = ""; bdc = 0
+        for (key in adir) {
+          split(key, kk, "|")
+          if (kk[1] == ba && !((key) in adone) && adir[key] > bdc) { bdc = adir[key]; bd = key }
+        }
+        if (bd == "") break
+        adone[bd] = 1
+        split(bd, kk, "|")
+        areas = areas (areas == "" ? "" : ",") kk[2]
+      }
+      tl = ""
+      for (key in atypes) { split(key, kk, "|"); if (kk[1] == ba) tl = tl (tl == "" ? "" : ",") kk[2] ":" atypes[key] }
+      ph = ""; phc = -1
+      for (key in ahours) { split(key, kk, "|"); if (kk[1] == ba && ahours[key] > phc) { phc = ahours[key]; ph = kk[2] } }
+      printf "AUTHOR: %s|commits=%d|ins=%d|del=%d|test_ratio=%s|top_areas=%s|types=%s|peak_hour=%s\n", ba, acommits[ba], ains[ba], adel[ba], tr, areas, tl, ph
+      if (abig[ba] != "") printf "AUTHOR_BIGGEST: %s|%s\n", ba, abig[ba]
+    }
+    # Weekly buckets, newest week first (w0 = week containing the newest commit).
+    for (w = 0; w <= maxwk; w++) {
+      if (wcommits[w] == 0) continue
+      wr = (wins[w] > 0 ? sprintf("%d%%", wtins[w] * 100 / wins[w]) : "n/a")
+      printf "WEEK: w%d|commits=%d|ins=%d|del=%d|test_ratio=%s\n", w, wcommits[w], wins[w], wdel[w], wr
+    }
+  }
+' || true
+
+# ── Co-author trailers: AI-assist count + human co-author credit lines ──────
+git log "$REF" "$_S" ${_U:+"$_U"} \
+    --format='%h %(trailers:key=Co-Authored-By,valueonly,separator=;)' 2>/dev/null | awk '
+  {
+    if (NF < 2) next
+    rest = substr($0, index($0, " ") + 1)
+    n = split(rest, tr, ";")
+    for (i = 1; i <= n; i++) {
+      t = tr[i]
+      if (t ~ /^[ \t]*$/) continue
+      if (tolower(t) ~ /(claude|copilot|codex|gemini|gpt|anthropic|openai|cursor|devin|\[bot\])/) { ai[$1] = 1 }
+      else { human++; if (human <= 40) printf "COAUTHOR: %s|%s\n", $1, t }
+    }
+  }
+  END {
+    if (human > 40) printf "COAUTHOR_LIST_TRUNCATED: showing 40 of %d\n", human
+    c = 0; for (h in ai) c++
+    printf "AI_ASSISTED_COMMITS: %d\n", c
+  }
+' || true
+
+# ── Logical SLOC added: non-blank, non-comment added lines in the window ────
+_LSLOC=$(git log "$REF" "$_S" ${_U:+"$_U"} -p --format= 2>/dev/null | awk '
+  /^\+/ && !/^\+\+\+/ {
+    l = substr($0, 2); gsub(/^[ \t]+|[ \t]+$/, "", l)
+    if (l == "") next
+    if (l ~ /^(\/\/|#|\*|\/\*|<!--|--)/) next
+    n++
+  }
+  END { print n + 0 }
+' || echo 0)
+echo "LOGICAL_SLOC_ADDED: ${_LSLOC:-0}"
+
+# ── PR/MR references in commit subjects (GitHub #NNN, GitLab !NNN) ──────────
+_PRS=$(git log "$REF" "$_S" ${_U:+"$_U"} --format='%s' 2>/dev/null | grep -oE '[#!][0-9]+' | sort -u | tr '\n' ' ' | sed 's/ $//' || true)
+echo "PRS_REFERENCED: $(printf '%s' "$_PRS" | wc -w | tr -d ' ')"
+[ -n "$_PRS" ] && echo "PR_REFS: $_PRS" || true
+
+# ── Test health (repo-wide + window) ─────────────────────────────────────────
+# Deliberately suffix-only (narrower than is_test's dir-based patterns): the
+# repo-wide census counts conventional test FILES; is_test additionally counts
+# dir-homed helpers toward test-insertion ratios.
+_TF_TOTAL=$(git ls-files 2>/dev/null | grep -cE '(\.test\.|\.spec\.|_test\.|_spec\.)' || true)
+case "$_TF_TOTAL" in ''|*[!0-9]*) _TF_TOTAL=0 ;; esac
+echo "TEST_FILES_TOTAL: $_TF_TOTAL"
+_REG=$(git log "$REF" "$_S" ${_U:+"$_U"} --oneline --grep="test(qa):" --grep="test(design):" --grep="test: coverage" 2>/dev/null || true)
+if [ -n "$_REG" ]; then
+  echo "REGRESSION_TEST_COMMITS: $(printf '%s\n' "$_REG" | wc -l | tr -d ' ')"
+  printf '%s\n' "$_REG" | sed 's/^/REGRESSION_COMMIT: /'
+else
+  echo "REGRESSION_TEST_COMMITS: 0"
+fi
+
+# ── Version range across the window (VERSION file, when tracked) ────────────
+if git cat-file -e "$REF:VERSION" 2>/dev/null; then
+  _V_LAST_C=$(git log "$REF" "$_S" ${_U:+"$_U"} --format=%H -- VERSION 2>/dev/null | head -1)
+  _V_FIRST_C=$(git log "$REF" "$_S" ${_U:+"$_U"} --format=%H -- VERSION 2>/dev/null | tail -1)
+  if [ -n "$_V_LAST_C" ]; then
+    _V_NEW=$(git show "$_V_LAST_C:VERSION" 2>/dev/null | head -1 | tr -d '[:space:]')
+    _V_OLD=$(git show "$_V_FIRST_C^:VERSION" 2>/dev/null | head -1 | tr -d '[:space:]')
+    [ -n "$_V_OLD" ] || _V_OLD=$(git show "$_V_FIRST_C:VERSION" 2>/dev/null | head -1 | tr -d '[:space:]')
+    echo "VERSION_RANGE: v$_V_OLD → v$_V_NEW"
+  else
+    _V_CUR=$(git show "$REF:VERSION" 2>/dev/null | head -1 | tr -d '[:space:]')
+    echo "VERSION_RANGE: v$_V_CUR (unchanged this window)"
+  fi
+fi
+
+# ── Streaks: consecutive commit days, full history (Step 11) ─────────────────
+# Anchored at the NEWEST commit date on the ref — the prose compares the anchor
+# against the session-reminder "today" (never the system clock) to decide
+# whether the streak is live or broken.
+_streak_awk='
+  function jdn(y, m, d) {
+    a = int((14 - m) / 12); yy = y + 4800 - a; mm = m + 12 * a - 3
+    return d + int((153 * mm + 2) / 5) + 365 * yy + int(yy / 4) - int(yy / 100) + int(yy / 400) - 32045
+  }
+  {
+    split($0, p, "-")
+    j = jdn(p[1] + 0, p[2] + 0, p[3] + 0)
+    if (NR == 1) { anchor = $0; prev = j; streak = 1; next }
+    if (j == prev - 1) { streak++; prev = j } else if (j != prev) exit
+  }
+  END { if (NR > 0) printf "%d days (anchor %s)\n", streak, anchor; else print "0 days (no commits)" }
+'
+_TEAM_STREAK=$(git log "$REF" --date=format-local:'%Y-%m-%d' --format='%ad' 2>/dev/null | awk '!seen[$0]++' | awk "$_streak_awk" || true)
+echo "TEAM_STREAK: ${_TEAM_STREAK:-0 days (no commits)}"
+if [ -n "$_USER_NAME" ]; then
+  _USER_STREAK=$(git log "$REF" --author="$_USER_NAME" --date=format-local:'%Y-%m-%d' --format='%ad' 2>/dev/null | awk '!seen[$0]++' | awk "$_streak_awk" || true)
+  echo "USER_STREAK: ${_USER_STREAK:-0 days (no commits)}"
+fi
+
+# ── Aux inputs (presence only — the model Reads what exists) ─────────────────
+[ -f "$_GH/retro-context.md" ]            && echo "RETRO_CONTEXT: present ($_GH/retro-context.md)"            || echo "RETRO_CONTEXT: absent"
+[ -f "$_GH/greptile-history.md" ]         && echo "GREPTILE_HISTORY: present ($_GH/greptile-history.md)"      || echo "GREPTILE_HISTORY: absent"
+[ -f "TODOS.md" ]                         && echo "TODOS_FILE: present (TODOS.md)"                            || echo "TODOS_FILE: absent"
+[ -f "$_GH/analytics/skill-usage.jsonl" ] && echo "SKILL_USAGE_LOG: present ($_GH/analytics/skill-usage.jsonl)" || echo "SKILL_USAGE_LOG: absent"
+[ -f "$_GH/analytics/eureka.jsonl" ]      && echo "EUREKA_LOG: present ($_GH/analytics/eureka.jsonl)"         || echo "EUREKA_LOG: absent"
+
+echo "RETRO_METRICS_END: ok"