mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-17 21:54:30 +01:00
Say when to use each gstack skill in Claude Code's skill list (GST-2774) (#4387)
* Say when to use each gstack skill in Claude Code's skill list (GST-2774) Claude Code's listing of each gstack skill now keeps a short when-to-use clause after its first sentence, so Opus 5.5 loads /review on "review my changes" and /plan-eng-review on "plan this feature" (GSTA-558). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Keep /review and /plan-eng-review within their size pins and refresh budgets CI on the first head found five size and fact checks the new catalog clause moved: the per-host SKILL.md size pins, the context-budget ceilings, the deslop-shared-libs catalog byte pin, the Claude ship golden and the catalog ceiling CLAUDE.md states. /review's and /plan-eng-review's full descriptions are now shorter than before, so their pins go down, and /plan-eng-review's scope gate is unchanged from main. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Say which skills keep no when-to-use clause in the changelog entry Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Update the catalog budget and voice-trigger docs for the when-to-use clause Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Drop "deploy this" from /ship's Claude Code skill list line Deploying belongs to /land-and-deploy, so /ship's when-to-use clause keeps "ship it, create a pr, push to main" only. Budgets, the size ledger and the Claude ship golden are re-measured. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Review-Finding: p1/specialist-batched#1 reader=specialist-batched Review-Finding: p1/red-team#1 reader=red-team Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Re-measure the setup-gbrain size cap after merging main Main grew setup-gbrain's always-loaded part to 38,621 bytes, and this branch's when-to-use clause adds 55 more, so the cap measured on the old base (38,637) is stale. The cap is now the merged measurement, 38,676. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
1 parent
127bcd6d55
commit
ab114c5308
83 files changed
+277
-216
No files matched your search
@@ -103,8 +103,20 @@ import { skillCensus } from './helpers/skill-census';
|
||||
* New-skill ratchet: previous ceiling 1,423 + ceil(115 / 4) = 1,452
|
||||
* token-equivalents (5,808 bytes), leaving 11 bytes. Existing descriptions
|
||||
* are unchanged.
|
||||
* ref GST-2774 when-to-use clause on base 0326b14 (2026-11-14)
|
||||
* result every trimmed Claude description keeps a when-to-use clause of at
|
||||
* most 64 chars (its triggers list, else its "Use when" sentence;
|
||||
* scripts/gen-skill-docs.ts buildTrimmedDescription), and /review,
|
||||
* /plan-eng-review and the root router reworded their leads;
|
||||
* measured 9,173 bytes = 2,294 token-equivalents, then 9,160
|
||||
* bytes = 2,290 after /ship's list dropped "deploy this" (it
|
||||
* belongs to /land-and-deploy). Deliberate
|
||||
* growth, not a new skill: in GSTA-558's trials Opus 5.5 skipped
|
||||
* /review on "review my changes" (0 of 3, 3 of 3 with the full
|
||||
* text) and loaded no planning skill on "plan this feature" (0 of 9).
|
||||
* New ceiling: 2,290 token-equivalents (9,160 bytes), leaving 0 bytes.
|
||||
*/
|
||||
const CATALOG_BUDGET_TOKEN_EQUIVALENTS = 1_452;
|
||||
const CATALOG_BUDGET_TOKEN_EQUIVALENTS = 2_290;
|
||||
|
||||
// Largest today: design-consultation at 229 bytes. A description that needs
|
||||
// more than 260 bytes is a body paragraph, not a catalog entry.
|
||||
|
||||
@@ -225,6 +225,37 @@ describe('buildTrimmedDescription', () => {
|
||||
});
|
||||
expect(out).toBe('Lead with whitespace. (gstack)');
|
||||
});
|
||||
|
||||
// GSTA-558: a lead alone says what a skill is, not when to load it, so the Claude catalog keeps a when-to-use clause.
|
||||
const parts = (lead: string, routingProse = '') => ({ lead, routingProse, voiceLine: null, hasGstackTag: true });
|
||||
|
||||
test('adds the triggers list as the when-to-use clause', () => {
|
||||
const out = buildTrimmedDescription(parts('Pre-landing PR review.', 'Use when asked to review.'), ['review my changes', 'look over my diff']);
|
||||
expect(out).toBe('Pre-landing PR review. Use for: review my changes, look over my diff. (gstack)');
|
||||
});
|
||||
|
||||
test('keeps only the triggers that fit the clause cap', () => {
|
||||
const out = buildTrimmedDescription(parts('Lead.'), ['first trigger here', 'second trigger here', 'third trigger here', 'fourth trigger here']);
|
||||
expect(out).toBe('Lead. Use for: first trigger here, second trigger here. (gstack)');
|
||||
});
|
||||
|
||||
test('without triggers, uses the "Use when" sentence from the routing prose', () => {
|
||||
const out = buildTrimmedDescription(parts('Quick fix.', 'Applies a patch. Use when asked to fix it. Proactively suggest it.'));
|
||||
expect(out).toBe('Quick fix. Use when asked to fix it. (gstack)');
|
||||
});
|
||||
|
||||
test('a lead that is already the "Use when" sentence is not repeated', () => {
|
||||
expect(buildTrimmedDescription(parts('Use when you review a diff.', 'Checks it.'))).toBe('Use when you review a diff. (gstack)');
|
||||
});
|
||||
|
||||
test('without triggers or a "Use when" sentence, the lead stands alone', () => {
|
||||
expect(buildTrimmedDescription(parts('A long lead sentence that says what the skill does.', 'More detail here.'))).toBe('A long lead sentence that says what the skill does. (gstack)');
|
||||
});
|
||||
|
||||
test('a lead that fills the catalog line gets no clause', () => {
|
||||
const lead = 'x'.repeat(200) + '.';
|
||||
expect(buildTrimmedDescription(parts(lead), ['review my changes'])).toBe(lead + ' (gstack)');
|
||||
});
|
||||
});
|
||||
|
||||
describe('applyCatalogTrim', () => {
|
||||
@@ -254,7 +285,10 @@ Original body content here.
|
||||
// The body gains no routing section: Claude Code reads a skill body only
|
||||
// after invocation, so routing prose there routes nothing.
|
||||
expect(content).not.toContain('## When to invoke this skill');
|
||||
expect(content).not.toContain('Use when asked to do an example task.');
|
||||
expect(content.slice(content.indexOf('\n---', 4))).not.toContain('Use when asked to do an example task.');
|
||||
// The catalog line keeps the when-to-use sentence (GSTA-558) and drops the rest of the routing prose.
|
||||
expect(content).toMatch(/^description: "?Example skill:[^\n]*\. Use when asked to do an example task\. \(gstack\)"?\n/m);
|
||||
expect(content).not.toContain('Proactively suggest');
|
||||
// Original body still present
|
||||
expect(content).toContain('# Example body');
|
||||
expect(content).toContain('Original body content here.');
|
||||
|
||||
Vendored
+63
-63
@@ -1,74 +1,74 @@
|
||||
{
|
||||
"_comment": "Context-budget ratchet ceilings (~tokens). Regenerate: bun test/helpers/capture-context-budget.ts. Headroom: alwaysOnTotal x1.05, eagerPerInvocation x1.1. Graded by test/context-budget-ratchet.test.ts via lib/context-bill.ts checkBudget.",
|
||||
"alwaysOnTotal": 8000,
|
||||
"alwaysOnTotal": 8647,
|
||||
"eagerPerInvocation": {
|
||||
"autoplan": 11289,
|
||||
"benchmark": 8043,
|
||||
"benchmark-models": 4086,
|
||||
"browse": 8943,
|
||||
"autoplan": 11306,
|
||||
"benchmark": 8420,
|
||||
"benchmark-models": 4454,
|
||||
"browse": 9311,
|
||||
"browser-skills/hackernews-frontpage": 371,
|
||||
"canary": 7738,
|
||||
"captain": 7211,
|
||||
"capy/skill/gstack": 5315,
|
||||
"careful": 1239,
|
||||
"codex": 9890,
|
||||
"context-restore": 6287,
|
||||
"context-save": 5101,
|
||||
"cso": 4902,
|
||||
"canary": 7750,
|
||||
"captain": 7282,
|
||||
"capy/skill/gstack": 5847,
|
||||
"careful": 1255,
|
||||
"codex": 9437,
|
||||
"context-restore": 6305,
|
||||
"context-save": 5118,
|
||||
"cso": 4916,
|
||||
"design-consultation": 10513,
|
||||
"design-html": 8896,
|
||||
"design-motion": 4724,
|
||||
"design-review": 22175,
|
||||
"design-shotgun": 9318,
|
||||
"deslop-shared-libs": 3411,
|
||||
"devex-review": 15303,
|
||||
"diagram": 4286,
|
||||
"document-generate": 6013,
|
||||
"document-release": 4454,
|
||||
"eval-plan": 5700,
|
||||
"freeze": 1115,
|
||||
"gstack": 5350,
|
||||
"design-html": 8996,
|
||||
"design-motion": 4738,
|
||||
"design-review": 22268,
|
||||
"design-shotgun": 9333,
|
||||
"deslop-shared-libs": 3420,
|
||||
"devex-review": 15442,
|
||||
"diagram": 4529,
|
||||
"document-generate": 6027,
|
||||
"document-release": 4469,
|
||||
"eval-plan": 6271,
|
||||
"freeze": 1163,
|
||||
"gstack": 5793,
|
||||
"gstack-upgrade": 6297,
|
||||
"guard": 1000,
|
||||
"health": 5816,
|
||||
"ios-clean": 2436,
|
||||
"ios-design-review": 2604,
|
||||
"ios-fix": 2307,
|
||||
"ios-qa": 5905,
|
||||
"ios-sync": 2465,
|
||||
"land-and-deploy": 13585,
|
||||
"landing-report": 3269,
|
||||
"learn": 2124,
|
||||
"make-pdf": 5204,
|
||||
"modernize": 3772,
|
||||
"office-hours": 11467,
|
||||
"open-gstack-browser": 4872,
|
||||
"guard": 1013,
|
||||
"health": 5558,
|
||||
"ios-clean": 2451,
|
||||
"ios-design-review": 2621,
|
||||
"ios-fix": 2312,
|
||||
"ios-qa": 5920,
|
||||
"ios-sync": 2482,
|
||||
"land-and-deploy": 8433,
|
||||
"landing-report": 3283,
|
||||
"learn": 2198,
|
||||
"make-pdf": 5493,
|
||||
"modernize": 3891,
|
||||
"office-hours": 11480,
|
||||
"open-gstack-browser": 5118,
|
||||
"openclaw/skills/gstack-openclaw-ceo-review": 2764,
|
||||
"openclaw/skills/gstack-openclaw-office-hours": 4433,
|
||||
"openclaw/skills/gstack-openclaw-retro": 2542,
|
||||
"pair-agent": 5293,
|
||||
"plan-ceo-review": 15776,
|
||||
"plan-design-review": 14687,
|
||||
"plan-devex-review": 12215,
|
||||
"plan-eng-review": 11369,
|
||||
"plan-tune": 9215,
|
||||
"qa": 7644,
|
||||
"qa-only": 5726,
|
||||
"retro": 13484,
|
||||
"review": 15417,
|
||||
"runaway-stopper": 4489,
|
||||
"scrape": 7312,
|
||||
"setup-browser-cookies": 3507,
|
||||
"setup-deploy": 5738,
|
||||
"setup-gbrain": 10009,
|
||||
"ship": 15913,
|
||||
"skillify": 5849,
|
||||
"spec": 9136,
|
||||
"sync-gbrain": 9749,
|
||||
"test-audit": 4622,
|
||||
"ubicloud": 3971,
|
||||
"unfreeze": 409,
|
||||
"verify": 2922,
|
||||
"write-skill": 2264
|
||||
"pair-agent": 5375,
|
||||
"plan-ceo-review": 15849,
|
||||
"plan-design-review": 14698,
|
||||
"plan-devex-review": 12229,
|
||||
"plan-eng-review": 10875,
|
||||
"plan-tune": 9304,
|
||||
"qa": 7669,
|
||||
"qa-only": 5743,
|
||||
"retro": 13501,
|
||||
"review": 15723,
|
||||
"runaway-stopper": 4576,
|
||||
"scrape": 7559,
|
||||
"setup-browser-cookies": 3749,
|
||||
"setup-deploy": 5751,
|
||||
"setup-gbrain": 10106,
|
||||
"ship": 16061,
|
||||
"skillify": 5864,
|
||||
"spec": 9152,
|
||||
"sync-gbrain": 9789,
|
||||
"test-audit": 4636,
|
||||
"ubicloud": 4059,
|
||||
"unfreeze": 423,
|
||||
"verify": 3231,
|
||||
"write-skill": 2386
|
||||
}
|
||||
}
|
||||
+1
-2
@@ -2,7 +2,7 @@
|
||||
name: ship
|
||||
preamble-tier: 4
|
||||
version: 1.0.0
|
||||
description: "Ship it: merge the base, run tests, review the diff, bump VERSION and CHANGELOG, push and create a PR. (gstack)"
|
||||
description: "Ship it: merge the base, run tests, review the diff, bump VERSION and CHANGELOG, push and create a PR. Use for: ship it, create a pr, push to main. (gstack)"
|
||||
allowed-tools:
|
||||
- Bash
|
||||
- Read
|
||||
@@ -17,7 +17,6 @@ triggers:
|
||||
- ship it
|
||||
- create a pr
|
||||
- push to main
|
||||
- deploy this
|
||||
---
|
||||
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
|
||||
<!-- Regenerate: bun run gen:skill-docs -->
|
||||
|
||||
+21
-21
@@ -5,53 +5,53 @@
|
||||
"agy/gstack-autoplan": 109449,
|
||||
"agy/gstack-plan-design-review": 109103,
|
||||
"agy/gstack-plan-devex-review": 114944,
|
||||
"agy/gstack-plan-eng-review": 143580,
|
||||
"agy/gstack-review": 104735,
|
||||
"agy/gstack-plan-eng-review": 143530,
|
||||
"agy/gstack-review": 104723,
|
||||
"codex/gstack-autoplan": 108192,
|
||||
"codex/gstack-plan-design-review": 110460,
|
||||
"codex/gstack-plan-devex-review": 116452,
|
||||
"codex/gstack-plan-eng-review": 144745,
|
||||
"codex/gstack-review": 104119,
|
||||
"codex/gstack-plan-eng-review": 144695,
|
||||
"codex/gstack-review": 104107,
|
||||
"copilot/gstack-autoplan": 108892,
|
||||
"copilot/gstack-plan-design-review": 109369,
|
||||
"copilot/gstack-plan-devex-review": 114406,
|
||||
"copilot/gstack-plan-eng-review": 143745,
|
||||
"copilot/gstack-review": 104316,
|
||||
"copilot/gstack-plan-eng-review": 143695,
|
||||
"copilot/gstack-review": 104304,
|
||||
"cursor/gstack-autoplan": 108124,
|
||||
"cursor/gstack-plan-design-review": 107911,
|
||||
"cursor/gstack-plan-devex-review": 113676,
|
||||
"cursor/gstack-plan-eng-review": 142335,
|
||||
"cursor/gstack-review": 122788,
|
||||
"cursor/gstack-plan-eng-review": 142285,
|
||||
"cursor/gstack-review": 122776,
|
||||
"factory/gstack-autoplan": 110402,
|
||||
"factory/gstack-plan-design-review": 111009,
|
||||
"factory/gstack-plan-devex-review": 117039,
|
||||
"factory/gstack-plan-eng-review": 145443,
|
||||
"factory/gstack-review": 126561,
|
||||
"factory/gstack-plan-eng-review": 145393,
|
||||
"factory/gstack-review": 126549,
|
||||
"gbrain/gstack-autoplan": 108531,
|
||||
"gbrain/gstack-plan-eng-review": 124963,
|
||||
"gbrain/gstack-plan-eng-review": 124932,
|
||||
"gemini/gstack-autoplan": 108682,
|
||||
"gemini/gstack-plan-design-review": 109197,
|
||||
"gemini/gstack-plan-devex-review": 114234,
|
||||
"gemini/gstack-plan-eng-review": 143578,
|
||||
"gemini/gstack-review": 104138,
|
||||
"gemini/gstack-plan-eng-review": 143528,
|
||||
"gemini/gstack-review": 104126,
|
||||
"hermes/gstack-autoplan": 108536,
|
||||
"hermes/gstack-plan-eng-review": 124999,
|
||||
"hermes/gstack-plan-eng-review": 124885,
|
||||
"kiro/gstack-autoplan": 107898,
|
||||
"kiro/gstack-plan-design-review": 107757,
|
||||
"kiro/gstack-plan-devex-review": 113528,
|
||||
"kiro/gstack-plan-eng-review": 142197,
|
||||
"kiro/gstack-review": 122612,
|
||||
"kiro/gstack-plan-eng-review": 142147,
|
||||
"kiro/gstack-review": 122600,
|
||||
"openclaw/gstack-autoplan": 108354,
|
||||
"openclaw/gstack-plan-eng-review": 123478,
|
||||
"openclaw/gstack-plan-eng-review": 123428,
|
||||
"opencode/gstack-autoplan": 108873,
|
||||
"opencode/gstack-plan-design-review": 109225,
|
||||
"opencode/gstack-plan-devex-review": 114284,
|
||||
"opencode/gstack-plan-eng-review": 143604,
|
||||
"opencode/gstack-review": 123410,
|
||||
"opencode/gstack-plan-eng-review": 143554,
|
||||
"opencode/gstack-review": 123398,
|
||||
"slate/gstack-autoplan": 108011,
|
||||
"slate/gstack-plan-design-review": 107834,
|
||||
"slate/gstack-plan-devex-review": 113602,
|
||||
"slate/gstack-plan-eng-review": 142266,
|
||||
"slate/gstack-review": 122700
|
||||
"slate/gstack-plan-eng-review": 142216,
|
||||
"slate/gstack-review": 122688
|
||||
}
|
||||
}
|
||||
@@ -161,7 +161,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
},
|
||||
behavioral: 'external',
|
||||
externalTest: 'test/skill-e2e-ship-section-loading.test.ts',
|
||||
maxSkeletonBytes: 61_438, // GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): Step 1's DIFF hint and the no-Eng-Review line name /plan-eng-review again, the wording GST-1698 removed; measured 61,438 (before: 61,417 on 81fb900). Before that: GSTA-152 token cap (2026-10-29, Garry's "Do it" on plan v3): the skeleton's Budget paragraph (the --token-cap, --resume and --continue flags, start/check/close, the budget-handoff pointer) and the section index's budget-handoff line; measured 61,420 (before: 60,958 on edf4c2e). Before that: GSTA-131 token efficiency (2026-10-27, Garry's D1): Step 1's delta carry (dry run, pregate at HEAD, then carry --pregate) and Step 11.5's fix-check and planned-skip binding, +60 bytes after tightening Step 1 and the Review policy paragraph; measured 60,960 (before: 60,900 on 10b77de4). Before that: GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): the hoisted skeleton (59,706) plus this PR's growth, keeping the hoist's 65-byte headroom; measured 60,848. Before: + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 78_275. + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): Step 16 stage 4 ZERO-RUN/unknown receipt rows, stage 5 honesty inventory, Step 17 open-gate ready-PR gate; measured 80,540 (2026-10-10). + rule 22 / GBRA-108 (2026-10-25): Step 22's terminal line (gstack-ship-receipt result, the GSTACK_RESULT line a parent greps) and Step 18's unattended routing (an open PR at HEAD gets its body updated, else handoff), offset in part by tightening Steps 14, 16, 18 and 20 prose after the 2026-10-14 tightening left 2 bytes of headroom; measured 81,535. + harness lane E (2026-10-26, issue row 3: four Captains re-ran /ship on identical product code): Step 1's carry check (gstack-ship-receipt carry binds an earlier receipt to HEAD when the product patch-id is unchanged); measured 82,165. + the Review policy paragraph (the blocking floor, pass structure and cap, NO FINDINGS, the review_loop receipt counters, the review_scope knob), stated in the skeleton because gstack is the canonical holder of its review policy (docs/review-policy.md); measured 82,645.
|
||||
maxSkeletonBytes: 61_467, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is), and /ship's list drops "deploy this", which belongs to /land-and-deploy; measured 61,467 (before: 61,438 on a141e94). Before that: GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): Step 1's DIFF hint and the no-Eng-Review line name /plan-eng-review again, the wording GST-1698 removed; measured 61,438 (before: 61,417 on 81fb900). Before that: GSTA-152 token cap (2026-10-29, Garry's "Do it" on plan v3): the skeleton's Budget paragraph (the --token-cap, --resume and --continue flags, start/check/close, the budget-handoff pointer) and the section index's budget-handoff line; measured 61,420 (before: 60,958 on edf4c2e). Before that: GSTA-131 token efficiency (2026-10-27, Garry's D1): Step 1's delta carry (dry run, pregate at HEAD, then carry --pregate) and Step 11.5's fix-check and planned-skip binding, +60 bytes after tightening Step 1 and the Review policy paragraph; measured 60,960 (before: 60,900 on 10b77de4). Before that: GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): the hoisted skeleton (59,706) plus this PR's growth, keeping the hoist's 65-byte headroom; measured 60,848. Before: + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 78_275. + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): Step 16 stage 4 ZERO-RUN/unknown receipt rows, stage 5 honesty inventory, Step 17 open-gate ready-PR gate; measured 80,540 (2026-10-10). + rule 22 / GBRA-108 (2026-10-25): Step 22's terminal line (gstack-ship-receipt result, the GSTACK_RESULT line a parent greps) and Step 18's unattended routing (an open PR at HEAD gets its body updated, else handoff), offset in part by tightening Steps 14, 16, 18 and 20 prose after the 2026-10-14 tightening left 2 bytes of headroom; measured 81,535. + harness lane E (2026-10-26, issue row 3: four Captains re-ran /ship on identical product code): Step 1's carry check (gstack-ship-receipt carry binds an earlier receipt to HEAD when the product patch-id is unchanged); measured 82,165. + the Review policy paragraph (the blocking floor, pass structure and cap, NO FINDINGS, the review_loop receipt counters, the review_scope knob), stated in the skeleton because gstack is the canonical holder of its review policy (docs/review-policy.md); measured 82,645.
|
||||
minUnionBytes: 181_000, // token-reduction Phases 1-2 (v1.69.x branch); measured union 201,464
|
||||
mustContain: ['VERSION', 'CHANGELOG', 'review', 'merge', 'PR'],
|
||||
// v1.58.5.0: pre-push-guard install (#2077) stacks on the shared first-run-guidance preamble.
|
||||
@@ -251,7 +251,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
// tier-2+ skeleton (measured 89,184). Main's v1.64.0.0 adds ~340 B more
|
||||
// (telemetry --error-message/--failed-step preamble prose, PR #769).
|
||||
// Budget covers the sum of both waves.
|
||||
maxSkeletonBytes: 56_209, // GSTA-134 skill diet (2026-10-28): lowered from 66_644 to the measured dieted skeleton, 56,209. Before: GSTA-96 hoist (2026-10-26): lowered from 85_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 581 bytes; measured 66,063. Before: Harness-aware outside voice: validated dispatch and provenance. + v1.91.19.0 wave: design --version probe (B4) and verdict-form outside voice (INV-1) on top of v1.91.17.0's round accounting (#3022); measured 80,443 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 84,669 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 84,804 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 84,863 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 84,748 (2026-10-07). Merged with the guard area: measured skeleton 84,945 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
maxSkeletonBytes: 56_252, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 56,252 (before: 56,209 on a141e94). Before that: GSTA-134 skill diet (2026-10-28): lowered from 66_644 to the measured dieted skeleton, 56,209. Before: GSTA-96 hoist (2026-10-26): lowered from 85_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 581 bytes; measured 66,063. Before: Harness-aware outside voice: validated dispatch and provenance. + v1.91.19.0 wave: design --version probe (B4) and verdict-form outside voice (INV-1) on top of v1.91.17.0's round accounting (#3022); measured 80,443 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 84,669 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 84,804 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 84,863 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 84,748 (2026-10-07). Merged with the guard area: measured skeleton 84,945 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
minUnionBytes: 99_200, // token-reduction Phases 1-2 (v1.69.x branch); measured union 110,293
|
||||
mustContain: ['design', 'visual'],
|
||||
maxSizeRatio: 1.12, // D1 1.104 + main's ~0.008
|
||||
@@ -356,10 +356,10 @@ do not launch the downstream skill or open a browser.`,
|
||||
// the #538 opt-out + D1 evidence directive — ratio 1.104 measured.
|
||||
// #2499 project-scope MCP jq in the brain-sync block grew every tier-2+
|
||||
// skeleton ~1.5KB (entry resolution emitted once per SKILL.md).
|
||||
maxSkeletonBytes: 43_885, // GSTA-134 skill diet (2026-10-28): lowered from 80_533 to the measured skeleton after the second opinion and visual design moved to sections, 43,885. Before: GSTA-96 hoist (2026-10-26): lowered from 95_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 952 bytes; measured 79,581. Before: Office-hours + sketch outside voices include host guards and completion checks. + v1.91.19.0 wave: Q<N> open-question prose form (#2729, approved Q3), DESIGN_READY --version probe (B4), Aside ~/.local/bin fallback (E7), verdict-form outside voice (INV-1), plus v1.91.17.0's round accounting (#3022) merged in; measured 89,684 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 92,590 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 92,869 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 92,930 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 92,756 (2026-10-07). Merged with the guard area: measured skeleton 93,099 (2026-10-07). + fix wave PR D: the Phase 4.5 builder-profile read before the session log (#2801) and the pre-telemetry design-doc check (#1049); measured skeleton 94,877 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
maxSkeletonBytes: 43_937, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 43,937 (before: 43,885 on a141e94). Before that: GSTA-134 skill diet (2026-10-28): lowered from 80_533 to the measured skeleton after the second opinion and visual design moved to sections, 43,885. Before: GSTA-96 hoist (2026-10-26): lowered from 95_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 952 bytes; measured 79,581. Before: Office-hours + sketch outside voices include host guards and completion checks. + v1.91.19.0 wave: Q<N> open-question prose form (#2729, approved Q3), DESIGN_READY --version probe (B4), Aside ~/.local/bin fallback (E7), verdict-form outside voice (INV-1), plus v1.91.17.0's round accounting (#3022) merged in; measured 89,684 (2026-10-03). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 92,590 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; skeleton measured 92,869 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; skeleton measured 92,930 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; skeleton measured 92,756 (2026-10-07). Merged with the guard area: measured skeleton 93,099 (2026-10-07). + fix wave PR D: the Phase 4.5 builder-profile read before the session log (#2801) and the pre-telemetry design-doc check (#1049); measured skeleton 94,877 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
minUnionBytes: 115_800, // Phase 4 wave 4; measured union 118,175
|
||||
mustContain: ['design doc', 'problem statement'],
|
||||
maxSizeRatio: 1.1990, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1990 (before: 1.1968). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1968 (before: 1.1922). Before that: GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): the handoff menu, its default and the design-doc line name /plan-eng-review again, +42 B union; measured 156,298 / 131,110 = 1.19211, rounded up (before: 156,256 = 1.19179 on 81fb900). Before that: GSTA-134 (2026-10-28, raised from 1.1796 by GStack Minder as merge-queue owner): +1,662 B union: second-opinion question moved into the main file while CODEX_SECOND_OPINION keeps its copy; per-run load 73,248→43,885 B; measured 156,286 / 131,110 = 1.19202, rounded up. Before: + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07). + empty LAST_ASSIGNMENT/LAST_PROJECT guards in the welcome_back and regular greetings (backfilled profiles); measured 153,469 / 131,110 = 1.1705 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file and its own copies of shared sections; measured 160,989 / 131,110 = 1.2279 (2026-10-25). Before: 1.18. - GSTA-96 dedupe: the Q<N> open-question form is office-hours' own appended subsection, so its copies of the shared Format and fallback subsections go; measured 154,653 / 131,110 = 1.1796 (2026-10-26), 154,624 = 1.1793 after the main merge. Before: 1.2279.
|
||||
maxSizeRatio: 1.1993, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 157,236 / 131,110 = 1.19927, rounded up (before: 1.1990). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1990 (before: 1.1968). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1968 (before: 1.1922). Before that: GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): the handoff menu, its default and the design-doc line name /plan-eng-review again, +42 B union; measured 156,298 / 131,110 = 1.19211, rounded up (before: 156,256 = 1.19179 on 81fb900). Before that: GSTA-134 (2026-10-28, raised from 1.1796 by GStack Minder as merge-queue owner): +1,662 B union: second-opinion question moved into the main file while CODEX_SECOND_OPINION keeps its copy; per-run load 73,248→43,885 B; measured 156,286 / 131,110 = 1.19202, rounded up. Before: + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 149,758 / 131,110 = 1.1422 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 150,037 / 131,110 = 1.1444 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 150,098 / 131,110 = 1.1448 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 150,011 / 131,110 = 1.1442 (2026-10-07). Merged with the guard area: measured 150,354 / 131,110 = 1.1468 (2026-10-07). + fix wave PR D: builder-profile read before the session log with Phase 6 using the carried values (#2801), the inline design doc before approval (#879) and the pre-telemetry design-doc check (#1049); measured 153,206 / 131,110 = 1.1685 (2026-10-07). + empty LAST_ASSIGNMENT/LAST_PROJECT guards in the welcome_back and regular greetings (backfilled profiles); measured 153,469 / 131,110 = 1.1705 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file and its own copies of shared sections; measured 160,989 / 131,110 = 1.2279 (2026-10-25). Before: 1.18. - GSTA-96 dedupe: the Q<N> open-question form is office-hours' own appended subsection, so its copies of the shared Format and fallback subsections go; measured 154,653 / 131,110 = 1.1796 (2026-10-26), 154,624 = 1.1793 after the main merge. Before: 1.2279.
|
||||
},
|
||||
'document-release': {
|
||||
skill: 'document-release',
|
||||
@@ -490,10 +490,10 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined, // operational multi-STOP skill, like ship
|
||||
},
|
||||
behavioral: 'plan',
|
||||
maxSkeletonBytes: 60_070, // GST-1088 lane B follow-up (raised from 60,014 to measured, no headroom): the Done-means check/waive commands run through the host-resolved bin path (~/.claude/skills/gstack/bin/gstack-skill-contract) instead of a bare gstack-skill-contract that a standard install doesn't put on PATH (fix-check finding on #3909 at 58aeee7), +56 bytes; measured 60,070. Before: GST-1088 lane B (#3909, raised from 59,774 to measured, no headroom; owner ruling via GStack Minder 2026-11-03): CONTRACT_CHECKER_SHIPPED=true now that bin/gstack-skill-contract ships (#3912) renders the gstack-skill-contract check/waive sentence under the Done means list (renders/GSTA-256/plan-v3.md line 74, r2-d6 "Done-means list"), +240 bytes; lane C's diet is expected to bring /review back under 59,073; measured 60,014. Before: GST-1088 lane B (raised from 59,073 to measured, no headroom): the contract: frontmatter block and the F1 "Done means" list rendered from it at the top of the body, plus widened triggers; F1 is a gate-rev-2 recommendation on the plan Garry approved with "do it" on gate rev 1 (2026-11-03), contingent on his gate-rev-2 answer, and lane C's diet is expected to bring /review back under 59,073; measured 59,774. Before: GSTA-96 hoist (2026-10-26): lowered from 80_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 319 bytes; measured 58,754. Before: Shared-code identity/skip/action rules + critical-severity validation; measured 74,493 (2026-09-17). + v1.91.12.0 merge of #2999 (review clarity repairs: await reads, research alongside dispatch, /review deadline and setup authority, findings sources) with #3002 (guarded state-root lines, plan-check checkpoints); each fit alone; measured 74,881 (2026-10-01). + Oct 8 wave: shared voice directive bans "load-bearing" and adds the reply-language rule, offset by tightening the bounded closer (net +17 bytes per tier-2+ skill); measured 74,884 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W2): Step 3.5 Diff scans with the shared GATE_SCAN_BLOCK, the Step 4 carry, the four-option `review-gate-disposition` question in 5c, gate record fields in 5.8 and the Gate edits report line; measured 80,054 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): Step 4's enum-only paragraph becomes the sideways sweep with the forced-CRITICAL list, plus the flake-fix number sentence in the Gate Integrity paragraph; measured skeleton 80,812 (2026-10-10).
|
||||
maxSkeletonBytes: 60_176, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 60,176 (before: 60,070 on a141e94). Before that: GST-1088 lane B follow-up (raised from 60,014 to measured, no headroom): the Done-means check/waive commands run through the host-resolved bin path (~/.claude/skills/gstack/bin/gstack-skill-contract) instead of a bare gstack-skill-contract that a standard install doesn't put on PATH (fix-check finding on #3909 at 58aeee7), +56 bytes; measured 60,070. Before: GST-1088 lane B (#3909, raised from 59,774 to measured, no headroom; owner ruling via GStack Minder 2026-11-03): CONTRACT_CHECKER_SHIPPED=true now that bin/gstack-skill-contract ships (#3912) renders the gstack-skill-contract check/waive sentence under the Done means list (renders/GSTA-256/plan-v3.md line 74, r2-d6 "Done-means list"), +240 bytes; lane C's diet is expected to bring /review back under 59,073; measured 60,014. Before: GST-1088 lane B (raised from 59,073 to measured, no headroom): the contract: frontmatter block and the F1 "Done means" list rendered from it at the top of the body, plus widened triggers; F1 is a gate-rev-2 recommendation on the plan Garry approved with "do it" on gate rev 1 (2026-11-03), contingent on his gate-rev-2 answer, and lane C's diet is expected to bring /review back under 59,073; measured 59,774. Before: GSTA-96 hoist (2026-10-26): lowered from 80_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 319 bytes; measured 58,754. Before: Shared-code identity/skip/action rules + critical-severity validation; measured 74,493 (2026-09-17). + v1.91.12.0 merge of #2999 (review clarity repairs: await reads, research alongside dispatch, /review deadline and setup authority, findings sources) with #3002 (guarded state-root lines, plan-check checkpoints); each fit alone; measured 74,881 (2026-10-01). + Oct 8 wave: shared voice directive bans "load-bearing" and adds the reply-language rule, offset by tightening the bounded closer (net +17 bytes per tier-2+ skill); measured 74,884 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W2): Step 3.5 Diff scans with the shared GATE_SCAN_BLOCK, the Step 4 carry, the four-option `review-gate-disposition` question in 5c, gate record fields in 5.8 and the Gate edits report line; measured 80,054 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): Step 4's enum-only paragraph becomes the sideways sweep with the forced-CRITICAL list, plus the flake-fix number sentence in the Gate Integrity paragraph; measured skeleton 80,812 (2026-10-10).
|
||||
minUnionBytes: 89_000, // Phase 4 wave 1; measured union 93,357
|
||||
mustContain: ['confidence', 'P1', 'P2', 'Review Army', 'adversarial'],
|
||||
maxSizeRatio: 1.3369, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.3369 (before: 1.3343). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.3343 (before: 1.3288). Before that: + GST-1088 lane B follow-up (raised from 1.3283 to measured, no headroom): the Done-means check/waive commands run through the host-resolved bin path instead of a bare gstack-skill-contract that isn't on PATH (fix-check finding on #3909 at 58aeee7), +56 bytes; measured 144,203 / 108,523 = 1.328778, rounded up. Before: + GST-1088 lane B (#3909, raised from 1.3261 to measured, no headroom; owner ruling via GStack Minder 2026-11-03): the gstack-skill-contract check/waive sentence that CONTRACT_CHECKER_SHIPPED=true renders (renders/GSTA-256/plan-v3.md line 74, r2-d6 "Done-means list"), +240 bytes; lane C's diet is expected to bring /review back under 1.3180; measured 144,147 / 108,523 = 1.32826, rounded up. Before: + GST-1088 lane B (raised from 1.3180 to measured, no headroom): the contract: frontmatter block and the F1 "Done means" list, contingent on Garry's gate-rev-2 answer; lane C's diet is expected to bring /review back under 1.3180; measured 143,907 / 108,523 = 1.3261. Before: + GSTA-167 variant G part 1 (plan approved by Garry 2026-10-30, autoplan-20261030161754 "Do it", which names about +0.3k prompt tokens per voice): the native adversarial and outside-voice prompts carry the blocking floor and the Severity and Blocks lines, +537 bytes; measured 1.3180 (2026-10-30). Before: 1.3136. GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): both owner-approved raises together, measured 142,550 / 108,523 = 1.3135. Before: Shared-code feature + critical-severity validation: 128,042 union bytes / 108,523 baseline = 1.1799; preserves content floors. + v1.91.12.0 merge of #2999 (above, plus plan-completion fallback intent and specialist checklist-by-path) with #3002; measured 1.1843 (2026-10-01). + v1.91.19.0 wave: verdict-form Codex callers with sandbox preflight (INV-1/B1), P0/P1 structured gate (B1b), bound-plan discovery and data-not-instructions guard (F1/D3), visible LEARNINGS failures (B5); measured 129,941 / 108,523 = 1.1974 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 130,025 / 108,523 = 1.1981 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051); measured 130,359 / 108,523 = 1.2012 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 131,314 / 108,523 = 1.2100 (2026-10-06). Combined Oct 6 wave head (A and B): measured 131,966 / 108,523 = 1.2160 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 132,199 / 108,523 = 1.2182 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 132,258 / 108,523 = 1.2187 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 132,233 / 108,523 = 1.2185 (2026-10-07). Merged with the guard area: measured 132,522 / 108,523 = 1.2211 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 133,902 / 108,523 = 1.2339 (2026-10-08). + gate integrity W2 (above); measured 1.282 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): sideways sweep and flake-fix number in Step 4; `Diff read` and `Undeclared behavior changes` in the review-mode Scope Check (plan-completion section); measured 140,497 / 108,523 = 1.2946 (2026-10-10). + harness lane E (2026-10-26): the lead-judgment stage in the finding merge and the `cause` anchor in the specialist prompts, shared with /ship through scripts/resolvers/review-army.ts; measured 141,949 / 108,523 = 1.3080.
|
||||
maxSizeRatio: 1.3378, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 145,176 / 108,523 = 1.33774, rounded up (before: 1.3369). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.3369 (before: 1.3343). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.3343 (before: 1.3288). Before that: + GST-1088 lane B follow-up (raised from 1.3283 to measured, no headroom): the Done-means check/waive commands run through the host-resolved bin path instead of a bare gstack-skill-contract that isn't on PATH (fix-check finding on #3909 at 58aeee7), +56 bytes; measured 144,203 / 108,523 = 1.328778, rounded up. Before: + GST-1088 lane B (#3909, raised from 1.3261 to measured, no headroom; owner ruling via GStack Minder 2026-11-03): the gstack-skill-contract check/waive sentence that CONTRACT_CHECKER_SHIPPED=true renders (renders/GSTA-256/plan-v3.md line 74, r2-d6 "Done-means list"), +240 bytes; lane C's diet is expected to bring /review back under 1.3180; measured 144,147 / 108,523 = 1.32826, rounded up. Before: + GST-1088 lane B (raised from 1.3180 to measured, no headroom): the contract: frontmatter block and the F1 "Done means" list, contingent on Garry's gate-rev-2 answer; lane C's diet is expected to bring /review back under 1.3180; measured 143,907 / 108,523 = 1.3261. Before: + GSTA-167 variant G part 1 (plan approved by Garry 2026-10-30, autoplan-20261030161754 "Do it", which names about +0.3k prompt tokens per voice): the native adversarial and outside-voice prompts carry the blocking floor and the Severity and Blocks lines, +537 bytes; measured 1.3180 (2026-10-30). Before: 1.3136. GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): both owner-approved raises together, measured 142,550 / 108,523 = 1.3135. Before: Shared-code feature + critical-severity validation: 128,042 union bytes / 108,523 baseline = 1.1799; preserves content floors. + v1.91.12.0 merge of #2999 (above, plus plan-completion fallback intent and specialist checklist-by-path) with #3002; measured 1.1843 (2026-10-01). + v1.91.19.0 wave: verdict-form Codex callers with sandbox preflight (INV-1/B1), P0/P1 structured gate (B1b), bound-plan discovery and data-not-instructions guard (F1/D3), visible LEARNINGS failures (B5); measured 129,941 / 108,523 = 1.1974 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 130,025 / 108,523 = 1.1981 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051); measured 130,359 / 108,523 = 1.2012 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 131,314 / 108,523 = 1.2100 (2026-10-06). Combined Oct 6 wave head (A and B): measured 131,966 / 108,523 = 1.2160 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 132,199 / 108,523 = 1.2182 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 132,258 / 108,523 = 1.2187 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 132,233 / 108,523 = 1.2185 (2026-10-07). Merged with the guard area: measured 132,522 / 108,523 = 1.2211 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 133,902 / 108,523 = 1.2339 (2026-10-08). + gate integrity W2 (above); measured 1.282 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): sideways sweep and flake-fix number in Step 4; `Diff read` and `Undeclared behavior changes` in the review-mode Scope Check (plan-completion section); measured 140,497 / 108,523 = 1.2946 (2026-10-10). + harness lane E (2026-10-26): the lead-judgment stage in the finding merge and the `cause` anchor in the specialist prompts, shared with /ship through scripts/resolvers/review-army.ts; measured 141,949 / 108,523 = 1.3080.
|
||||
},
|
||||
codex: {
|
||||
skill: 'codex',
|
||||
@@ -544,8 +544,8 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined, // operational skill
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 32_216, // GSTA-161 skill diet (2026-10-30): lowered from 52_682 to the measured skeleton, 32,216; Step 7's canary script, the Aside contract, the browser fallback and Third-Party Web Actions moved to sections/canary.md. Before: GSTA-96 hoist (2026-10-26): lowered from 74_500 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 690 bytes; measured 51,992. Before: + Aside browser contract for Step 7 canary ({{ASIDE_SETUP}}); measured 73_523
|
||||
maxSizeRatio: 1.1344, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1344 (before: 1.1318). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1318 (before: 1.1260). Before that: + #3318 Step 3.4 reads the ship policy and prints one VERSION_CHECK verdict (owner-approved raise, Garry 2026-10-24: "do it"); measured 1.1201 (2026-10-24). Before: 1.1120. + v1.81 Aside contract + gstack-browser fallback block; measured 1.077. + both untrusted-content marker formats in the browser fallback (W7f) + the readiness gate's project test command and live eval-store paths (s06 H6/H7); measured 1.1076 (2026-10-02). Re-measured 1.0943 (2026-10-03); cap = measured + 0.005 headroom. + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort); measured 115,226 / 104,578 = 1.1018 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 117,753 / 104,578 = 1.1260 (2026-10-25). Before: 1.125.
|
||||
maxSkeletonBytes: 32_273, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 32,273 (before: 32,216 on a141e94). Before that: GSTA-161 skill diet (2026-10-30): lowered from 52_682 to the measured skeleton, 32,216; Step 7's canary script, the Aside contract, the browser fallback and Third-Party Web Actions moved to sections/canary.md. Before: GSTA-96 hoist (2026-10-26): lowered from 74_500 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 690 bytes; measured 51,992. Before: + Aside browser contract for Step 7 canary ({{ASIDE_SETUP}}); measured 73_523
|
||||
maxSizeRatio: 1.1350, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 118,689 / 104,578 = 1.13493, rounded up (before: 1.1344). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1344 (before: 1.1318). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1318 (before: 1.1260). Before that: + #3318 Step 3.4 reads the ship policy and prints one VERSION_CHECK verdict (owner-approved raise, Garry 2026-10-24: "do it"); measured 1.1201 (2026-10-24). Before: 1.1120. + v1.81 Aside contract + gstack-browser fallback block; measured 1.077. + both untrusted-content marker formats in the browser fallback (W7f) + the readiness gate's project test command and live eval-store paths (s06 H6/H7); measured 1.1076 (2026-10-02). Re-measured 1.0943 (2026-10-03); cap = measured + 0.005 headroom. + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort); measured 115,226 / 104,578 = 1.1018 (2026-10-07). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 117,753 / 104,578 = 1.1260 (2026-10-25). Before: 1.125.
|
||||
minUnionBytes: 91_000, // Phase 4 wave 1; estimated union ~94.9KB
|
||||
mustContain: ['readiness', 'merge', 'canary', 'revert', 'staging'],
|
||||
},
|
||||
@@ -583,7 +583,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
maxSkeletonBytes: 48_175, // GSTA-96 hoist (2026-10-26): lowered from 70_000 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 4,888 bytes; measured 43,287. Before: Phase-specific outside coverage, native fallback, and harness guard.
|
||||
minUnionBytes: 85_000, // measured union 86,926
|
||||
mustContain: ['6 Decision Principles', 'TASTE DECISION', 'USER CHALLENGE', 'consensus', 'Restore Point'],
|
||||
maxSizeRatio: 1.1799, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1799 (before: 1.1772). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1772 (before: 1.1723). Before that: GST-537 /autoplan --ceo-only (GStack Minder approved A1, 2026-10-31): sections/ceo-only.md (2,168 B) plus its Section index row, read only when the invocation names --ceo-only (test/autoplan-ceo-only.test.ts pins that a normal run never reads it); measured 119,545 / 101,979 = 1.1723 (2026-10-31), +2,276 B over main's 117,269 = 1.1499. Before: 1.1511. Four validated outside invocations replace raw CLI calls; phases keep independent coverage. + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 114,297 / 101,979 = 1.1208 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 114,533 / 101,979 = 1.1231 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site, and phase-close publishing each report with the `true autoplan-published <phase>` no-op before the next phase entry in a later message (CEO-1); measured 114,320 / 101,979 = 1.1210 (2026-10-07). Merged with the guard area: measured 115,149 / 101,979 = 1.1291 (2026-10-07). + Oct 8 wave (permission cards after a background reviewer): Step 1 puts RESTORE_PATH, and so every phase artifact, in the project's git-excluded `.gstack/tmp/autoplan/`, which Claude Code reads without a card after the skill turn ends; measured 115,270 / 101,979 = 1.1303 (2026-10-08). + fix wave PR D: the prerequisite offer is skipped in spawned/headless sessions (#1958); measured 115,267 / 101,979 = 1.1303 (2026-10-07). Both merged: measured 115,126 / 101,979 = 1.1289 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave B9/B10/B12: Phase 0 ESTIMATE and the phase-close timing record, the final gate as a gate list (`gstack-gate render/parse`, stable ids, gate_rev) and the URGENT block above the summary, offset by tightening the Phase 4 prose and the tasks-section; measured 114,980 / 101,979 = 1.1275 (2026-10-10). + Oct 10 multi-agent wave PR D1 (reality rows): the reality-rows check line in the CEO and Eng phase files, the Pre-Gate rule (unattended miss is `incomplete`, never a warning) and the two Pre-Gate cells; measured 117,042 / 101,979 = 1.1477 (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 117,388 / 101,979 = 1.1511 (2026-10-25). Before: 1.149.
|
||||
maxSizeRatio: 1.1804, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 120,374 / 101,979 = 1.18038, rounded up (before: 1.1799). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1799 (before: 1.1772). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1772 (before: 1.1723). Before that: GST-537 /autoplan --ceo-only (GStack Minder approved A1, 2026-10-31): sections/ceo-only.md (2,168 B) plus its Section index row, read only when the invocation names --ceo-only (test/autoplan-ceo-only.test.ts pins that a normal run never reads it); measured 119,545 / 101,979 = 1.1723 (2026-10-31), +2,276 B over main's 117,269 = 1.1499. Before: 1.1511. Four validated outside invocations replace raw CLI calls; phases keep independent coverage. + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 114,297 / 101,979 = 1.1208 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 114,533 / 101,979 = 1.1231 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site, and phase-close publishing each report with the `true autoplan-published <phase>` no-op before the next phase entry in a later message (CEO-1); measured 114,320 / 101,979 = 1.1210 (2026-10-07). Merged with the guard area: measured 115,149 / 101,979 = 1.1291 (2026-10-07). + Oct 8 wave (permission cards after a background reviewer): Step 1 puts RESTORE_PATH, and so every phase artifact, in the project's git-excluded `.gstack/tmp/autoplan/`, which Claude Code reads without a card after the skill turn ends; measured 115,270 / 101,979 = 1.1303 (2026-10-08). + fix wave PR D: the prerequisite offer is skipped in spawned/headless sessions (#1958); measured 115,267 / 101,979 = 1.1303 (2026-10-07). Both merged: measured 115,126 / 101,979 = 1.1289 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave B9/B10/B12: Phase 0 ESTIMATE and the phase-close timing record, the final gate as a gate list (`gstack-gate render/parse`, stable ids, gate_rev) and the URGENT block above the summary, offset by tightening the Phase 4 prose and the tasks-section; measured 114,980 / 101,979 = 1.1275 (2026-10-10). + Oct 10 multi-agent wave PR D1 (reality rows): the reality-rows check line in the CEO and Eng phase files, the Pre-Gate rule (unattended miss is `incomplete`, never a warning) and the two Pre-Gate cells; measured 117,042 / 101,979 = 1.1477 (2026-10-10). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 117,388 / 101,979 = 1.1511 (2026-10-25). Before: 1.149.
|
||||
},
|
||||
spec: {
|
||||
skill: 'spec',
|
||||
@@ -612,7 +612,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 36_571, // GSTA-96 hoist (2026-10-26): lowered from 58_400 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 1,606 bytes; measured 34,965. Before: + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 57_356
|
||||
minUnionBytes: 64_500, // measured union 67,430
|
||||
maxSizeRatio: 1.0853, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.0853 (before: 1.0819). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.0819 (before: 1.0746). Before that: Oct 10 multi-agent wave PR E2: the lazy gate-and-file section renders {{COORDINATOR_CONTRACT}} (the block every spawned lane inherits word for word; `gstack-autoplan contract` prints the same bytes) before the --execute spawn pipe; measured 86,614 / 81,577 = 1.0617 after the contract became a fail-closed `CONTRACT=$(…)` capture (2026-10-10). The skeleton is unchanged (57,107). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 87,656 / 81,577 = 1.0745 (2026-10-25). Before: 1.07.
|
||||
maxSizeRatio: 1.0860, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 88,590 / 81,577 = 1.08597, rounded up (before: 1.0853). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.0853 (before: 1.0819). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.0819 (before: 1.0746). Before that: Oct 10 multi-agent wave PR E2: the lazy gate-and-file section renders {{COORDINATOR_CONTRACT}} (the block every spawned lane inherits word for word; `gstack-autoplan contract` prints the same bytes) before the --execute spawn pipe; measured 86,614 / 81,577 = 1.0617 after the contract became a fail-closed `CONTRACT=$(…)` capture (2026-10-10). The skeleton is unchanged (57,107). + GSTA-96 shared-preamble hoist (owner-approved raise, Garry 2026-10-25: "do it"): the union now holds sections/preamble.md, so a fresh invocation reads the pointer plus the shared file; measured 87,656 / 81,577 = 1.0745 (2026-10-25). Before: 1.07.
|
||||
mustContain: ['HARD GATE', 'dedupe', 'quality gate', 'acceptance criteria', 'archive'],
|
||||
},
|
||||
'setup-gbrain': {
|
||||
@@ -640,7 +640,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined,
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 38_629, // GSTA-96 hoist (2026-10-26): lowered from 60_450 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 323 bytes; measured 38,306. Before: + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 60_013
|
||||
maxSkeletonBytes: 38_676, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 38,676 (before: 38,629 on a141e94). Before that: GSTA-96 hoist (2026-10-26): lowered from 60_450 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 323 bytes; measured 38,306. Before: + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 60_013
|
||||
minUnionBytes: 78_300, // measured union 79,139
|
||||
mustContain: ['PGLite', 'Supabase', 'claude mcp add', 'read_secret_to_env', 'pooler'],
|
||||
maxSizeRatio: 1.07, // measured 1.051 vs the branch monolith: index + stubs + 4 STOP pointers
|
||||
@@ -677,7 +677,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 41_669, // GSTA-96 hoist (2026-10-26): lowered from 63_500 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 12,415 bytes; measured 29,254. Before: + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} (replaces the browse setup block); measured 61_253
|
||||
maxSizeRatio: 1.1526, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1526 (before: 1.1493). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1493 (before: 1.1420). Before that: + v1.81 Aside contract + gstack-browser fallback block (1.080 on v1.91.7.0) + the shared test value bar at 8a.5 ({{TEST_VALUE_BAR:qa}}); measured 1.094 + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.101 (2026-09-30) + v1.91.12.0 merge of #2999 (await scope/method Reads, capture --after checkpoints, browser-only empty evidence list) with #3002; measured 1.1028 (2026-10-01). + both untrusted-content marker formats in the browser fallback (W7f); measured 1.1035 (2026-10-02). Re-measured 1.1038 after the W8 probe-loop renames (2026-10-03); the cap already matches. + the annotate-every-capture and superseded rule before materialize (a ship-exploratory-late-input run published evidence that omitted older-snapshot captures); measured 1.1064 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 93,282 / 84,049 = 1.1099 (2026-10-04). + reliability follow-ups C2 (judge-named gaps after trimming the added wording: feasible 180 s Browser Quick, PROBE_DIR's source line, stop goes to the §4 report, written JSON keeps full card values; lane S's {user}/timing fields); measured 93,311 / 84,049 = 1.11020 (2026-10-04). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 94,486 / 84,049 = 1.1242 (2026-10-06). + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort); measured 94,681 / 84,049 = 1.1265 (2026-10-07). + Oct 8 wave: shared voice directive bans "load-bearing" and adds the reply-language rule, offset by tightening the bounded closer (net +17 bytes per tier-2+ skill); measured 94,736 / 84,049 = 1.12715 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
maxSizeRatio: 1.1533, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 96,928 / 84,049 = 1.15323, rounded up (before: 1.1526). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.1526 (before: 1.1493). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.1493 (before: 1.1420). Before that: + v1.81 Aside contract + gstack-browser fallback block (1.080 on v1.91.7.0) + the shared test value bar at 8a.5 ({{TEST_VALUE_BAR:qa}}); measured 1.094 + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.101 (2026-09-30) + v1.91.12.0 merge of #2999 (await scope/method Reads, capture --after checkpoints, browser-only empty evidence list) with #3002; measured 1.1028 (2026-10-01). + both untrusted-content marker formats in the browser fallback (W7f); measured 1.1035 (2026-10-02). Re-measured 1.1038 after the W8 probe-loop renames (2026-10-03); the cap already matches. + the annotate-every-capture and superseded rule before materialize (a ship-exploratory-late-input run published evidence that omitted older-snapshot captures); measured 1.1064 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 93,282 / 84,049 = 1.1099 (2026-10-04). + reliability follow-ups C2 (judge-named gaps after trimming the added wording: feasible 180 s Browser Quick, PROBE_DIR's source line, stop goes to the §4 report, written JSON keeps full card values; lane S's {user}/timing fields); measured 93,311 / 84,049 = 1.11020 (2026-10-04). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 94,486 / 84,049 = 1.1242 (2026-10-06). + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort); measured 94,681 / 84,049 = 1.1265 (2026-10-07). + Oct 8 wave: shared voice directive bans "load-bearing" and adds the reply-language rule, offset by tightening the bounded closer (net +17 bytes per tier-2+ skill); measured 94,736 / 84,049 = 1.12715 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
minUnionBytes: 69_500, // measured union 70,385
|
||||
// 'aside repl' pins the Aside contract; '$B goto' pins the fallback block in the always-loaded skeleton.
|
||||
mustContain: ['bug', 'aside repl', '$B goto', 'fix', 'Health Score Rubric', 'regression'],
|
||||
@@ -714,7 +714,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined,
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 35_574, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 35,574 (before: 35_298). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 35,298 (before: 34_700). Before that: + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} skeleton + the STOP-Read pointer; measured 29_986 + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 32,532 (2026-10-06). + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort), and the cookbook's silent-failure list and signed-in-tab recipe (the rule details live here, not in every browsing skill); skeleton measured 34,047 (2026-10-07). + Oct 8 wave: the tier-1 voice directive bans "load-bearing" and adds the reply-language rule (tier 1 has no closer to tighten: +158 bytes); skeleton measured 34,209 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
maxSkeletonBytes: 35_635, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 35,635 (before: 35,574 on a141e94). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 35,574 (before: 35_298). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 35,298 (before: 34_700). Before that: + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} skeleton + the STOP-Read pointer; measured 29_986 + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); skeleton measured 32,532 (2026-10-06). + Oct 7 wave B6: Aside rules 1, 4, 6 and 7 (offer a target-origin tab before openTab, a second sign-in wall means a tab- or URL-bound session, no early-return hint, fast [ok without the sentinel is an abort), and the cookbook's silent-failure list and signed-in-tab recipe (the rule details live here, not in every browsing skill); skeleton measured 34,047 (2026-10-07). + Oct 8 wave: the tier-1 voice directive bans "load-bearing" and adds the reply-language rule (tier 1 has no closer to tighten: +158 bytes); skeleton measured 34,209 (2026-10-08). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
minUnionBytes: 36_000, // skeleton + command-list section (14,240); measured union ~38.5 KB
|
||||
// 'BEGIN/END UNTRUSTED EXTERNAL' pins the untrusted-content warning in the
|
||||
// command reference; 'aside repl' pins the Aside contract in the skeleton.
|
||||
@@ -733,7 +733,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined,
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 51_626, // GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): the EUREKA example names /plan-eng-review again; measured 51,626 (before: 51,619 on 81fb900). Before that: GSTA-96 hoist (2026-10-26): lowered from 73_450 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 937 bytes; measured 50,685. Before: + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 73_059
|
||||
maxSkeletonBytes: 51_669, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 51,669 (before: 51,626 on a141e94). Before that: GST-2726 (2026-11-15, Garry: bring /plan-eng-review back): the EUREKA example names /plan-eng-review again; measured 51,626 (before: 51,619 on 81fb900). Before that: GSTA-96 hoist (2026-10-26): lowered from 73_450 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 937 bytes; measured 50,685. Before: + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 73_059
|
||||
minUnionBytes: 66_000, // measured union 73,496
|
||||
mustContain: ['retrospective', '45-minute gap', 'Ship of the week', 'Praise'],
|
||||
},
|
||||
@@ -757,10 +757,10 @@ do not launch the downstream skill or open a browser.`,
|
||||
// No section-loading paid case yet: a new periodic case would push the
|
||||
// periodic census past its 38-slice cap (test/paid-retry-supervision.test.ts).
|
||||
behavioral: 'none',
|
||||
maxSkeletonBytes: 85_182, // /design-review --build (GST-1741 PR 2, 2026-11-07, grant: GStack Minder, 2026-11-07): --build routing, stop pointer, index row, description clause and trigger: +443 B, trimmed 130; the build-loop section is mode-loaded; measured 85,182. Before: GSTA-134 skill diet (2026-10-28): lowered from 115_947 to the measured skeleton after the outside voices and test bootstrap moved to sections, 84,869. Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the hoisted skeleton plus main's headroom of 0 bytes; measured 115,947 on the merged tree. Before: measured 137735 on the merged tree with main f27a760 (2026-10-27, #3507); 137767 (2026-10-26; 137773 on 2026-10-25 before the shorter craft-audit trigger): the Section index the external-host carve test requires, its craft-audit row, and the STOP pointer (GSTA-92; Garry 2026-10-25 'Do it' (GSTA-92)).
|
||||
maxSkeletonBytes: 85_222, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 85,222 (before: 85,182 on a141e94). Before that: /design-review --build (GST-1741 PR 2, 2026-11-07, grant: GStack Minder, 2026-11-07): --build routing, stop pointer, index row, description clause and trigger: +443 B, trimmed 130; the build-loop section is mode-loaded; measured 85,182. Before: GSTA-134 skill diet (2026-10-28): lowered from 115_947 to the measured skeleton after the outside voices and test bootstrap moved to sections, 84,869. Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the hoisted skeleton plus main's headroom of 0 bytes; measured 115,947 on the merged tree. Before: measured 137735 on the merged tree with main f27a760 (2026-10-27, #3507); 137767 (2026-10-26; 137773 on 2026-10-25 before the shorter craft-audit trigger): the Section index the external-host carve test requires, its craft-audit row, and the STOP pointer (GSTA-92; Garry 2026-10-25 'Do it' (GSTA-92)).
|
||||
minUnionBytes: 136_100, // GSTA-134 skill diet (2026-10-28): measured union 137,602 (lowered from 143_300); before: measured union 144802 on the merged tree with main f27a760 (2026-10-27, #3507); 145037 (2026-10-26)
|
||||
mustContain: ['AI Slop Detection', 'Fix Loop', 'gstack-design-lint', 'Proof beside each claim', 'holds session data'],
|
||||
maxSizeRatio: 1.3654, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.3654 (before: 1.3628). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.3628 (before: 1.357). Before that: /design-review --build (GST-1741 PR 2, 2026-11-07, grant: GStack Minder, 2026-11-07): --build routing, stop pointer, index row, description clause and trigger: +443 B, trimmed 130; the build-loop section is mode-loaded; measured 143,620 / 105,842 = 1.35693. Before: 1.3001, GSTA-134 skill diet (2026-10-28): measured 137,602 / 105,842 = 1.30007, rounded up (lowered from 1.3739). Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the union now holds sections/preamble.md (the hoist's owner-approved raise, decision A) on top of main's 1.3681; measured 145,410 / 105,842 = 1.3739 on the merged tree. Before: first parity guard for design-review: measured 144802 / 105,842 = 1.3681 on the merged tree with main f27a760 (2026-10-27, #3507: the design lint swap); before that 145082 / 105,842 = 1.3708 (2026-10-25; 145077 after the /ship review fixes, 145068 = 1.3707 after the line-13 reword, 145049 = 1.3705 after the post-merge /ship review, 145037 = 1.3704 after its second pass, 2026-10-26), the skeleton's growth since v1.64.1.0 plus the craft audit (Garry 2026-10-25 'Do it' (GSTA-92)).
|
||||
maxSizeRatio: 1.3657, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 144,546 / 105,842 = 1.36568, rounded up (before: 1.3654). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 1.3654 (before: 1.3628). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 1.3628 (before: 1.357). Before that: /design-review --build (GST-1741 PR 2, 2026-11-07, grant: GStack Minder, 2026-11-07): --build routing, stop pointer, index row, description clause and trigger: +443 B, trimmed 130; the build-loop section is mode-loaded; measured 143,620 / 105,842 = 1.35693. Before: 1.3001, GSTA-134 skill diet (2026-10-28): measured 137,602 / 105,842 = 1.30007, rounded up (lowered from 1.3739). Before: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): the union now holds sections/preamble.md (the hoist's owner-approved raise, decision A) on top of main's 1.3681; measured 145,410 / 105,842 = 1.3739 on the merged tree. Before: first parity guard for design-review: measured 144802 / 105,842 = 1.3681 on the merged tree with main f27a760 (2026-10-27, #3507: the design lint swap); before that 145082 / 105,842 = 1.3708 (2026-10-25; 145077 after the /ship review fixes, 145068 = 1.3707 after the line-13 reword, 145049 = 1.3705 after the post-merge /ship review, 145037 = 1.3704 after its second pass, 2026-10-26), the skeleton's growth since v1.64.1.0 plus the craft audit (Garry 2026-10-25 'Do it' (GSTA-92)).
|
||||
},
|
||||
|
||||
// ── Token-reduction Phase 4 wave 4 (v1.69.x branch): design doctrine carve ──
|
||||
@@ -790,7 +790,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined, // operational skill, no plan-mode gate
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 34_410, // GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): lowered from 56_200 by the shared preamble that moved to sections/preamble.md, keeping main's headroom of 366 bytes; measured 34,044 on the merged tree. Before: measured 55,834 on the merged tree with main f27a760 (2026-10-27, #3507: the Step 4 lint line); 55,786 (2026-10-25): the craft section pointer, its index row and the Step 4 craft-check line (GSTA-92); before that 55,262 (2026-09-09): the detector install offer pointer + its sections-table row (the brief itself lives in sections/detector-install-offer.md); before that 54,545 for the review-cycle trust prose, the Slop Gate's Decisions-Log clause, and the blacklist header's override sentence + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
maxSkeletonBytes: 34_427, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 34,427 (before: 34,410 on a141e94). Before that: GSTA-96 hoist merged with v1.91.274.0 (#3507, 2026-10-27): lowered from 56_200 by the shared preamble that moved to sections/preamble.md, keeping main's headroom of 366 bytes; measured 34,044 on the merged tree. Before: measured 55,834 on the merged tree with main f27a760 (2026-10-27, #3507: the Step 4 lint line); 55,786 (2026-10-25): the craft section pointer, its index row and the Step 4 craft-check line (GSTA-92); before that 55,262 (2026-09-09): the detector install offer pointer + its sections-table row (the brief itself lives in sections/detector-install-offer.md); before that 54,545 for the review-cycle trust prose, the Slop Gate's Decisions-Log clause, and the blacklist header's override sentence + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10).
|
||||
minUnionBytes: 57_500, // Phase 4 wave 4; measured union 58,682; 78,626 on the merged tree with main f27a760 (2026-10-27, #3507)
|
||||
mustContain: ["Don't make me think", "Users scan, they don't read", 'The Goodwill Reservoir', 'PRETEXT API CHEATSHEET', 'Pattern 3: Text around obstacles'],
|
||||
},
|
||||
@@ -853,7 +853,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
},
|
||||
behavioral: 'external',
|
||||
externalTest: 'test/skill-e2e-design.test.ts',
|
||||
maxSkeletonBytes: 18_112, // GSTA-96 hoist (2026-10-27): lowered from 39_900 by the shared preamble that moved to sections/preamble.md, keeping main's headroom of 32 bytes; measured 18,080 on the v1.91.273.0 merge. Before: new skill (GSTA-92 plan item 15, Garry 2026-10-25 "Do it"); measured skeleton 39,836 (2026-10-25)
|
||||
maxSkeletonBytes: 18_132, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 18,132 (before: 18,112 on a141e94). Before that: GSTA-96 hoist (2026-10-27): lowered from 39_900 by the shared preamble that moved to sections/preamble.md, keeping main's headroom of 32 bytes; measured 18,080 on the v1.91.273.0 merge. Before: new skill (GSTA-92 plan item 15, Garry 2026-10-25 "Do it"); measured skeleton 39,836 (2026-10-25)
|
||||
minUnionBytes: 57_500, // measured union 58,666 (2026-10-25)
|
||||
mustContain: ['window.__start()', 'window.__tick(dt)', 'whole milliseconds averaging 1000/60', 'Content never hides behind animation timing'],
|
||||
},
|
||||
@@ -900,7 +900,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
gateAfterStop: undefined, // operational skill, no plan-mode gate
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 32_169, // GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 32,169 (before: 31_893). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 31,893 (before: 31_300). Before that: first carve: Section index, one STOP pointer and the vet rule on the 29.9k monolith; measured 30,781 (2026-10-26)
|
||||
maxSkeletonBytes: 32_225, // GST-2774 (2026-11-14): the Claude catalog description keeps a when-to-use clause (GSTA-558: Opus 5.5 skipped /review and the planning skills when the listing said only what a skill is); measured 32,225 (before: 32,169 on a141e94). Before that: GST-2756 (2026-11-15, Garry's "Do it" to the ask-once and open-every-file habits): two Ground Rules lines (ask each question once and carry it as one waiting line; open every handed-over file and remove placeholders), +276 bytes; measured 32,169 (before: 31_893). Before that: GST-2753 (2026-11-15, Garry's "Do it" to moving the never-print-secrets rule into gstack): the shared Ground Rules preamble section (never print a whole environment, git config or process table; wait on CI with one gstack-pr-wait call), +614 bytes; measured 31,893 (before: 31_300). Before that: first carve: Section index, one STOP pointer and the vet rule on the 29.9k monolith; measured 30,781 (2026-10-26)
|
||||
minUnionBytes: 33_000, // skeleton + vet-the-number section; measured union 34,527 (2026-10-26)
|
||||
mustContain: ['performance.getEntries()', 'REGRESSION', 'Name the limiter', 'run-to-run variation', 'inconclusive'],
|
||||
// The v1.64.1.0 baseline measured the 37.2k monolith; the carved union is below it.
|
||||
|
||||
@@ -167,10 +167,11 @@ describe('shared-code skill distribution', () => {
|
||||
}
|
||||
});
|
||||
|
||||
test('standalone catalog entry adds exactly the approved 82 bytes', () => {
|
||||
// 82 approved bytes, plus 36 for the when-to-use clause every Claude catalog entry gained in GST-2774 and the YAML quotes it needs.
|
||||
test('standalone catalog entry adds exactly the approved 118 bytes', () => {
|
||||
const skill = readFileSync(join(output, 'deslop-shared-libs/SKILL.md'), 'utf8');
|
||||
const description = skill.match(/^description: (.+)$/m)?.[1];
|
||||
expect(description).toBe('Find worthwhile shared-code extractions in recent work. (gstack)');
|
||||
expect(Buffer.byteLength('deslop-shared-libs') + Buffer.byteLength(description!)).toBe(82);
|
||||
expect(description).toBe('"Find worthwhile shared-code extractions in recent work. Use for: find code worth sharing. (gstack)"');
|
||||
expect(Buffer.byteLength('deslop-shared-libs') + Buffer.byteLength(description!)).toBe(118);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"bytes": 29,
|
||||
"why": "GST-2774: the Claude catalog description keeps a when-to-use clause (Use for: ship it, create a pr, push to main)"
|
||||
}
|
||||
@@ -41,6 +41,8 @@ describe('routerLine (router-mode targets)', () => {
|
||||
l => { expect(l).toStartWith('Use when asked to'); expect(l).not.toContain('Pre-landing'); }],
|
||||
['no trigger sentence: the triggers list leads', 'Pre-landing PR review. Analyzes the diff.', TRIGGERS, 160,
|
||||
l => expect(l).toStartWith('Use for: review this pr, code review')],
|
||||
['the catalog-trimmed "Use for:" clause gives way to the full triggers list', 'Pre-landing PR review. Use for: review this pr, code review. (gstack)', TRIGGERS, 160,
|
||||
l => expect(l).toBe('Use for: review this pr, code review, check my diff, pre-landing review. Pre-landing PR review.')],
|
||||
['neither: the first sentence, cut at a word', 'A very long first sentence about a workflow that goes on and on and on.', [], 40,
|
||||
l => { expect(l).toStartWith('A very long first sentence'); expect(l).toEndWith('...'); }],
|
||||
];
|
||||
|
||||
Reference in new issue
Block a user