ETHOS 9, Earn Its Place: factory, /write-skill and /autoplan carry it

Garry, 2026-11-02: "Also work this principle of only include it if it is
beneficial and good into gstack". ETHOS.md principle 9 states the rule, the
fair test (claude_code preset, frontier models per R54, masked no-gstack
arm), the R48 Why-null cycle, the safety exception, and measure biggest
first, linking docs/inventory.md. factory.md item 8 cites it, trimmed
elsewhere to 3,298 of 3,300 bytes with no rule dropped. /write-skill's edit
ladder step 2 is the evidence rule and section 4 adds the Evidence: commit
line. /autoplan's CEO phase lists each part a plan adds to gstack with its
evidence or owned, dated plan; two redundant lines went to keep autoplan
under its size pins (pins lowered by 17). CONTRIBUTING.md "Adding a new
skill" and docs/skills.md point at the ledger.

Skill-Size: 3273→3666 bytes (write-skill/SKILL.md.tmpl)
Skill-Size: 12738→12721 bytes (autoplan/sections/ceo-phase.md)
Evidence: plan none (owner ruling R56, GST-914); write-skill and autoplan rows stay grandfathered untested
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

CONTRIBUTING.md

@@ -811,6 +811,7 @@ Write or change skill prose with `/write-skill` (edit ladder, levels, `gstack-sk
 3. The dynamic template discovery picks it up for every host render and for `gstack/llms.txt`. Two things it does not fill in: a row in `SKILL_REQUIREMENTS` in `lib/doctor-components.ts` (the doctor's `--for <skill>` table; `test/doctor-components.test.ts` fails on a skill directory without one, and the same gen run rerenders `bin/gstack-doctor-components.sh`), and the catalog rows readers find the skill through (README.md, AGENTS.md, `docs/skills.md`, `docs/PROJECT_STRUCTURE.md`, the root `SKILL.md.tmpl` router)
 4. Budget it: run `bun test/helpers/capture-context-budget.ts` and commit the refreshed `test/fixtures/context-budget.json` — the context-budget ratchet fails any skill without a ceiling; the catalog budget (`test/catalog-budget.test.ts`) fails until its cap is ratcheted by the protocol in its failure message, and the number is quoted in CLAUDE.md, this file and `docs/CONTRIBUTOR_REFERENCE.md`
 5. Commit `{skill}/SKILL.md` (and the generated `{skill}/sections/preamble.md` when the template's `preamble-tier` is 2 or higher), external host output is generated at setup time and gitignored
+6. Give it a row in the evidence ledger, `docs/inventory/evidence.json` ([ETHOS.md: 9. Earn Its Place](ETHOS.md#9-earn-its-place)): evidence that it helps on frontier models (`sources`, `models`, `prompt: preset`, `scope`, `masked: true`), or `status: untested` with its `reason`, a concrete `plan` (a `test/fixtures/skill-evals/<skill>/tasks.json` or an /eval-plan preregistration), an `owner` and a `measure_by` date. `test/inventory.test.ts` fails on a skill without a valid row; `bin/gstack-inventory --check` names the problem, and `bin/gstack-inventory` refreshes the dated snapshot in `docs/inventory.md`
 
 ## Conductor workspaces
 

ETHOS.md

@@ -273,6 +273,42 @@ the eval that jumps twenty points usually found a shortcut, not a capability.
 
 ---
 
+## 9. Earn Its Place
+
+Garry, 2026-11-02:
+"Also work this principle of only include it if it is beneficial and good into gstack".
+
+Every skill, step, instruction, check and default costs tokens and attention
+on every run that loads it. So each one earns its place. A new part comes with
+evidence that it helps on frontier models, or with a stated reason, an owner
+and a date by which a fair test will measure it.
+
+A fair test runs Claude Code's own system prompt (the `claude_code` preset,
+not the Agent SDK's stub), on frontier models (today Opus 5.5 and GPT-6.1 Sol,
+plus at most one named low-cost model), against a no-gstack arm that is masked
+so it cannot read gstack. A result from the stub, from Haiku or Sonnet alone,
+or from an unmasked arm is a lead, not a verdict.
+
+When a fair test shows an existing part doesn't help, it gets one "Why null?"
+cycle: did the model use the part, did the task fit, was there enough power and
+room below the ceiling, and does today's model do the job without it. Then
+keep it, fix the method, or cut it, and say which plainly.
+
+Safety and security guards (careful, freeze, guard, unfreeze, cso) stay on
+their stated reason: they stop the rare bad run that an average score can't see.
+
+Measure the biggest parts first, the ones that load the most on the most runs.
+[docs/inventory.md](docs/inventory.md) ranks every part by load and shows its
+evidence; `docs/inventory/evidence.json` is the ledger, and
+`bin/gstack-inventory --check` validates it.
+
+**Anti-patterns:**
+- A new step because it sounds wise, with no test planned.
+- Keeping a part because it looked good on the stub or a small model.
+- Cutting a part after one null result, without the Why-null cycle.
+
+---
+
 ## How They Work Together
 
 Boil the Ocean says: **cover the whole requirement with the least code.**
@@ -282,6 +318,7 @@ Attack the Premise says: **when fixes keep failing, test the belief they share.*
 Separate Before Serializing says: **remove the race before you referee it.**
 Make Operations Idempotent says: **design for the run that happens twice.**
 Explain the Number says: **a result you cannot explain is not yet a result.**
+Earn Its Place says: **every part shows it helps, or has a dated plan to.**
 
 Together: search first, then build the complete version of the right thing.
 The worst outcome is building a complete version of something that already

autoplan/sections/ceo-phase.md

@@ -11,11 +11,12 @@ announcement. Dispatching a reviewer never completes its step.
 - Premises: accept reasonable ones (P6). Queue clearly-wrong/challenged premises
   as User Challenges for Phase 4: assumption, reason and cost of proceeding.
   The user decides there; never stop mid-pipeline.
+- List each part the plan adds to gstack (skill, step, instruction, check, default) with its
+  evidence or owned, dated test plan; a missing one is a finding.
 - Alternatives: pick highest completeness (P1). If tied, pick simplest (P5).
   If top 2 are close → mark TASTE DECISION.
 - Scope expansion: in blast radius + <1d CC → approve (P2). Outside → defer to TODOS.md (P3).
   Duplicates → reject (P4). Borderline (3-5 files) → mark TASTE DECISION.
-- All 11 review sections: run fully, auto-decide each issue, log every decision.
 
 **Required execution checklist (CEO):**
 
@@ -38,8 +39,7 @@ Before every spec dispatch, including after each accepted spec fix, run:
 ```bash
 bun "<SNAPSHOT_TOOL>" amend-input ceo "<ACTIVE_PLAN>" "<CEO_STEP0_CHECKPOINT>" "<RESTORE_PATH>" "<methodologyPath>"
 ```
-This applies the recorded requirements and exports the complete current
-`Implementation plan`. Keep returned `checkpointPath` as the amendment baseline;
+Keep returned `checkpointPath` as the amendment baseline;
 use returned `reviewInputPath` as `<CEO_SPEC_INPUT>`. Read that file at every
 returned `readRanges` offset/limit through EOF, then read the CEO scope summary in full.
 Reconcile dispositions, scope counts, proposal IDs and actual heading/test references

autoplan/sections/ceo-phase.md.tmpl

@@ -9,11 +9,12 @@ announcement. Dispatching a reviewer never completes its step.
 - Premises: accept reasonable ones (P6). Queue clearly-wrong/challenged premises
   as User Challenges for Phase 4: assumption, reason and cost of proceeding.
   The user decides there; never stop mid-pipeline.
+- List each part the plan adds to gstack (skill, step, instruction, check, default) with its
+  evidence or owned, dated test plan; a missing one is a finding.
 - Alternatives: pick highest completeness (P1). If tied, pick simplest (P5).
   If top 2 are close → mark TASTE DECISION.
 - Scope expansion: in blast radius + <1d CC → approve (P2). Outside → defer to TODOS.md (P3).
   Duplicates → reject (P4). Borderline (3-5 files) → mark TASTE DECISION.
-- All 11 review sections: run fully, auto-decide each issue, log every decision.
 
 **Required execution checklist (CEO):**
 
@@ -36,8 +37,7 @@ Before every spec dispatch, including after each accepted spec fix, run:
 ```bash
 bun "<SNAPSHOT_TOOL>" amend-input ceo "<ACTIVE_PLAN>" "<CEO_STEP0_CHECKPOINT>" "<RESTORE_PATH>" "<methodologyPath>"
 ```
-This applies the recorded requirements and exports the complete current
-`Implementation plan`. Keep returned `checkpointPath` as the amendment baseline;
+Keep returned `checkpointPath` as the amendment baseline;
 use returned `reviewInputPath` as `<CEO_SPEC_INPUT>`. Read that file at every
 returned `readRanges` offset/limit through EOF, then read the CEO scope summary in full.
 Reconcile dispositions, scope counts, proposal IDs and actual heading/test references

capy/skill/gstack/factory.md

@@ -1,17 +1,17 @@
-# How we work: the gstack software factory on Capy
+# How we work: gstack's factory on Capy
 
-What seven Captain crews converged on (2026-10-29). Your crew's CREW.md and recorded approvals decide who may merge, update a base, spend or touch production; urgency changes priority, never permissions or gates. With no Captain, ask the person and never merge without their word. Story: capy/README.md; examples: your org Drive's software-factory/README.md, if any.
+What seven Captain crews agreed on. Your crew's CREW.md and recorded approvals decide who may merge, update a base, spend or touch production; urgency changes priority, never permissions or gates. With no Captain, ask the person; never merge without their word. Story: capy/README.md; examples: org Drive software-factory/README.md.
 
 1. **Plan, then a yes.** New functionality starts with /autoplan sized to the work; the build waits for "do it". [SKILL.md: Plan, approve, ship]
 2. **Someone else merges.** Run /ship to a receipt on your final pushed head, send one READY quoting gstack's verify output verbatim, and stop. The merge owner merges on green and assigns versions. [docs/captain.md: The READY contract]
 3. **Block only on the floor.** A finding blocks if it would fail a test, break production, or lose data or secrets; the rest goes in the PR body or next wave. [docs/review-policy.md]
 4. **Fix waves.** When main goes red, hold /ship while one owner finds the root cause; bring main in once, as your rules allow. Fold deferred findings and test follow-ups into one PR. [docs/triage.md]
-5. **Severe first, same gates.** A severe user-facing bug jumps the queue; the plan can be short; receipt, checks and merge owner stay.
-6. **Trade findings, not small talk.** Another crew's finding goes to its Captain, through yours, with the evidence.
+5. **Severe first, same gates.** A severe user-facing bug jumps the queue with a short plan; receipt, checks and merge owner stay.
+6. **Trade findings, not small talk.** Another crew's finding goes to its Captain, through yours, with evidence.
 7. **Measure before you act.** Run the real system on the merged tree you ship; a real run outranks a reviewed plan. Each number names its run, commit or uncapped query; say what you did not verify.
-8. **Evals decide, and losses get reported.** Preregister bars, cap and stop rule before paying [/eval-plan]. Cheap proof (a keyless fake, a smoke) before the paid run. Use controls (no-skill and placebo arms, clean decoys). Report use and pass apart; quote spend from the meter.
-9. **Flakes: one rerun, a ledger, a daily fix.** Only the rerun the policy allows, never a harness or infra red; a second red is real; no test is loosened. [docs/captain.md: The daily flaky pass]
+8. **Evals decide, and losses get reported.** Preregister bars, cap and stop rule before paying [/eval-plan]. Cheap proof (a keyless fake, a smoke) first. Controls: no-skill and placebo arms, clean decoys. Report use and pass apart; quote spend from the meter. A new part needs proof it helps or a dated test plan [ETHOS.md: 9. Earn Its Place].
+9. **Flakes: one rerun, a ledger, a daily fix.** Only the policy's rerun, never for a harness or infra red; a second red is real; never loosen a test. [docs/captain.md: The daily flaky pass]
 10. **Quiet.** Message on a decision, a blocker, a READY or a finished phase. A broadcast needing no reply goes in the Captain's notes; never reply just to acknowledge.
-11. **Ask once, plainly.** One ask per decision, explained like the owner is five: your Captain's name, then a lettered line each: "A: <code> hit problem p, which happens when h. We could do 1) x, 2) y or 3) z. Recommendation x because why. A1 to take recommendation." "do it" takes every recommendation; "A2" takes option 2. Owner tasks: the exact link (in Capy: path and field), numbered simple steps, the reply word. Never re-ask a standing rule; check what you can yourself. [docs/captain.md: The ask format]
+11. **Ask once, plainly.** One ask per decision, explained like the owner is five: your Captain's name, then a lettered line each: "A: <code> hit problem p, which happens when h. We could do 1) x, 2) y or 3) z. Recommendation x because why. A1 to take recommendation." "do it" takes every recommendation; "A2" takes option 2. Owner tasks: the exact link (in Capy: path and field), numbered steps, the reply word. Never re-ask a standing rule; check what you can yourself. [docs/captain.md: The ask format]
 12. **Fresh threads, closed out.** One thread per unit of work (crew threads ask their Captain); past the context limit, hand off. Its Captain archives only its crew's threads; threads outside every crew are the owner's, even its automation's. Size reviews to the diff; read the token counter. [docs/ship-budget.md]
 13. **The owner's model preference.** `gstack-models resolve --role agent` picks agent models, except cross-family voices and eval subjects. [docs/model-policy.md: Your model preference]

docs/skills.md

@@ -908,8 +908,12 @@ gstack's own templates and for any skill folder you own.
   add nothing a fresh session already does; edit the line that covers the idea instead of appending; put the fact on the
   lowest level that reaches the agent in time (description, SKILL.md, `references/`, the tool's `--help`, the tool's
   errors); write the rule and put the story in the commit message.
+- **Evidence.** A new skill, step, instruction, check or default needs evidence that it helps on frontier models, or a
+  dated plan to measure it ([ETHOS.md: 9. Earn Its Place](../ETHOS.md#9-earn-its-place)). Commits carry an `Evidence:`
+  line, and every gstack skill has a row in the evidence ledger, `docs/inventory/evidence.json`, which
+  [docs/inventory.md](inventory.md) ranks by load per run.
 - **Size.** `gstack-skill-bill` prints bytes and estimated tokens per level, and in a gstack checkout the skill's eval
-  task file (`EVAL TASKS:`). Commits carry
+  task file (`EVAL TASKS:`) and its ledger row (`EVIDENCE:`). Commits carry
   `Skill-Size: <before>→<after> bytes`; a skill more than 10% over its last `Skill-Diet:` commit is DUE, and a red
   context-budget ratchet means diet, not a higher ceiling.
 - **Drift.** `test/skill-bin-drift.test.ts` fails when a template or rendered skill calls a gstack bin or flag that

test/capy-skill-wrapper.test.ts

@@ -594,6 +594,15 @@ describe('capy skill: factory.md, the auto-loaded "how we work" page', () => {
     expect(citationProblems(text)).toEqual([]);
   });
 
+  test('item 8 cites ETHOS.md principle 9, Earn Its Place, which states the fair test, the Why-null cycle and the safety exception', () => {
+    const item8 = fs.readFileSync(FACTORY, 'utf8').split('\n').find(l => l.startsWith('8. '))!;
+    expect(item8).toContain('[ETHOS.md: 9. Earn Its Place]');
+    const ethos = fs.readFileSync(path.join(REPO, 'ETHOS.md'), 'utf8');
+    const p9 = ethos.slice(ethos.indexOf('## 9. Earn Its Place'), ethos.indexOf('## How They Work Together'));
+    expect(p9.length).toBeGreaterThan(200);
+    for (const words of ['only include it if it is beneficial and good', 'claude_code', 'Opus 5.5', 'GPT-6.1 Sol', 'masked', 'Why null?', 'Safety and security guards', 'biggest', 'docs/inventory.md']) expect(p9).toContain(words);
+  });
+
   test('negative controls: a missing file, a missing heading and an unknown skill are each caught', () => {
     expect(citationProblems('[docs/no-such-page.md: Anything]')).toEqual(['missing file docs/no-such-page.md']);
     expect(citationProblems('[docs/captain.md: No Such Heading]')).toEqual(['missing heading docs/captain.md: No Such Heading']);

test/fixtures/skill-md-size-allowlist.json

@@ -2,53 +2,53 @@
   "_comment": "Generated SKILL.md files over the limit, pinned at their exact character count (#3199). test/skill-md-size-guard.test.ts fails when a pinned skill grows past its pin or shrinks below it: lower the pin when a skill shrinks and delete it once the skill is within the limit. Raising a pin is an owner decision. The shared-preamble hoist (GSTA-96) moved every tier 2+ skill's shared preamble into sections/preamble.md; the pins below are what remains.",
   "limit": 100000,
   "pins": {
-    "agy/gstack-autoplan": 109666,
+    "agy/gstack-autoplan": 109649,
     "agy/gstack-plan-design-review": 109116,
     "agy/gstack-plan-devex-review": 114957,
     "agy/gstack-plan-eng-review": 143590,
     "agy/gstack-review": 104276,
-    "codex/gstack-autoplan": 108409,
+    "codex/gstack-autoplan": 108392,
     "codex/gstack-plan-design-review": 110473,
     "codex/gstack-plan-devex-review": 116465,
     "codex/gstack-plan-eng-review": 144755,
     "codex/gstack-review": 103799,
-    "copilot/gstack-autoplan": 109109,
+    "copilot/gstack-autoplan": 109092,
     "copilot/gstack-plan-design-review": 109382,
     "copilot/gstack-plan-devex-review": 114419,
     "copilot/gstack-plan-eng-review": 143755,
     "copilot/gstack-review": 103857,
-    "cursor/gstack-autoplan": 108341,
+    "cursor/gstack-autoplan": 108324,
     "cursor/gstack-plan-design-review": 107924,
     "cursor/gstack-plan-devex-review": 113689,
     "cursor/gstack-plan-eng-review": 142345,
     "cursor/gstack-review": 122147,
-    "factory/gstack-autoplan": 110619,
+    "factory/gstack-autoplan": 110602,
     "factory/gstack-plan-design-review": 111022,
     "factory/gstack-plan-devex-review": 117052,
     "factory/gstack-plan-eng-review": 145453,
     "factory/gstack-review": 125920,
-    "gbrain/gstack-autoplan": 108748,
+    "gbrain/gstack-autoplan": 108731,
     "gbrain/gstack-plan-eng-review": 124972,
-    "gemini/gstack-autoplan": 108899,
+    "gemini/gstack-autoplan": 108882,
     "gemini/gstack-plan-design-review": 109210,
     "gemini/gstack-plan-devex-review": 114247,
     "gemini/gstack-plan-eng-review": 143588,
     "gemini/gstack-review": 103679,
-    "hermes/gstack-autoplan": 108751,
+    "hermes/gstack-autoplan": 108734,
     "hermes/gstack-plan-eng-review": 125008,
-    "kiro/gstack-autoplan": 108115,
+    "kiro/gstack-autoplan": 108098,
     "kiro/gstack-plan-design-review": 107770,
     "kiro/gstack-plan-devex-review": 113541,
     "kiro/gstack-plan-eng-review": 142207,
     "kiro/gstack-review": 121971,
-    "openclaw/gstack-autoplan": 108571,
+    "openclaw/gstack-autoplan": 108554,
     "openclaw/gstack-plan-eng-review": 123487,
-    "opencode/gstack-autoplan": 109090,
+    "opencode/gstack-autoplan": 109073,
     "opencode/gstack-plan-design-review": 109238,
     "opencode/gstack-plan-devex-review": 114297,
     "opencode/gstack-plan-eng-review": 143614,
     "opencode/gstack-review": 122769,
-    "slate/gstack-autoplan": 108228,
+    "slate/gstack-autoplan": 108211,
     "slate/gstack-plan-design-review": 107847,
     "slate/gstack-plan-devex-review": 113615,
     "slate/gstack-plan-eng-review": 142276,

write-skill/SKILL.md

@@ -102,8 +102,8 @@ telemetry — it never blocks the workflow.
 
 ## 1. Find the skill
 
-Run `~/.claude/skills/gstack/bin/gstack-skill-bill <name|folder>`. It resolves exact names only and prints the
-skill's kind and its size per level. A new skill: make the folder first (in a gstack checkout, follow CONTRIBUTING.md
+Run `~/.claude/skills/gstack/bin/gstack-skill-bill <name|folder>`. It prints the skill's kind,
+its size per level and its `EVIDENCE:` row. A new skill: make the folder first (in a gstack checkout, follow CONTRIBUTING.md
 "Adding a new skill"), then write every line by sections 2 and 3.
 - `user`: edit it in place.
 - `gstack-install`: never edit; gstack-upgrade overwrites it. Edit `<skill>/SKILL.md.tmpl` in a gstack checkout, or
@@ -126,7 +126,9 @@ Put each fact on the lowest level that still reaches the agent before it needs i
 
 Stop at the first step that handles the change.
 1. **Fix it below the skill.** A clearer error, a flag, a check or a test in the tool. Prose is for judgment calls.
-2. **Check the model needs it.** If a fresh session does the right thing without the line, add nothing.
+2. **Earn its place.** Add a skill, step, instruction, check or default only with evidence it helps frontier models
+   or a dated plan to measure it (skill-evals `tasks.json` or an /eval-plan prereg). If a fresh session does it right
+   without the line, add nothing.
 3. **Edit, don't append.** Change the line that already covers the idea; each meaning lives in one place.
 4. **Pick its level** (section 2).
 5. **Rule, not story.** One positive rule under a short name; the incident goes in the commit message.
@@ -138,6 +140,8 @@ When code changes a name or flag a skill teaches, update the skill in the same c
 
 - Run `~/.claude/skills/gstack/bin/gstack-skill-bill` before and after, and put `Skill-Size: <before>→<after> bytes (<file>)` in the commit
   message. DUE means it grew over 10% since its last `Skill-Diet:` commit: diet it instead of adding.
+- Add `Evidence: <run id, results file or commit>`, `Evidence: plan <tasks.json or prereg> measure_by <date>` or
+  `Evidence: safety: <reason>`. A new gstack skill adds its `docs/inventory/evidence.json` row (`gstack-inventory --check`).
 - In a gstack checkout: `bun test test/skill-bin-drift.test.ts test/parity-suite.test.ts` and the budgets in
   CONTRIBUTING.md. A red context-budget ratchet means diet, not a higher ceiling.
 - Rerun the case that prompted the change in a fresh session.

write-skill/SKILL.md.tmpl

@@ -29,8 +29,8 @@ allowed-tools:
 
 ## 1. Find the skill
 
-Run `~/.claude/skills/gstack/bin/gstack-skill-bill <name|folder>`. It resolves exact names only and prints the
-skill's kind and its size per level. A new skill: make the folder first (in a gstack checkout, follow CONTRIBUTING.md
+Run `~/.claude/skills/gstack/bin/gstack-skill-bill <name|folder>`. It prints the skill's kind,
+its size per level and its `EVIDENCE:` row. A new skill: make the folder first (in a gstack checkout, follow CONTRIBUTING.md
 "Adding a new skill"), then write every line by sections 2 and 3.
 - `user`: edit it in place.
 - `gstack-install`: never edit; gstack-upgrade overwrites it. Edit `<skill>/SKILL.md.tmpl` in a gstack checkout, or
@@ -53,7 +53,9 @@ Put each fact on the lowest level that still reaches the agent before it needs i
 
 Stop at the first step that handles the change.
 1. **Fix it below the skill.** A clearer error, a flag, a check or a test in the tool. Prose is for judgment calls.
-2. **Check the model needs it.** If a fresh session does the right thing without the line, add nothing.
+2. **Earn its place.** Add a skill, step, instruction, check or default only with evidence it helps frontier models
+   or a dated plan to measure it (skill-evals `tasks.json` or an /eval-plan prereg). If a fresh session does it right
+   without the line, add nothing.
 3. **Edit, don't append.** Change the line that already covers the idea; each meaning lives in one place.
 4. **Pick its level** (section 2).
 5. **Rule, not story.** One positive rule under a short name; the incident goes in the commit message.
@@ -65,6 +67,8 @@ When code changes a name or flag a skill teaches, update the skill in the same c
 
 - Run `~/.claude/skills/gstack/bin/gstack-skill-bill` before and after, and put `Skill-Size: <before>→<after> bytes (<file>)` in the commit
   message. DUE means it grew over 10% since its last `Skill-Diet:` commit: diet it instead of adding.
+- Add `Evidence: <run id, results file or commit>`, `Evidence: plan <tasks.json or prereg> measure_by <date>` or
+  `Evidence: safety: <reason>`. A new gstack skill adds its `docs/inventory/evidence.json` row (`gstack-inventory --check`).
 - In a gstack checkout: `bun test test/skill-bin-drift.test.ts test/parity-suite.test.ts` and the budgets in
   CONTRIBUTING.md. A red context-budget ratchet means diet, not a higher ceiling.
 - Rerun the case that prompted the change in a fresh session.