RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat(skills): claimed limitations now require evidence, everywhere + wave follow-ups filed 

Every tier-2+ skill's preamble gains one directive distilled from nine live
release failures in two days on the fork: a claimed limitation or
requirement ('the API can't do this', 'X requires a credential',
'impossible on this platform') is a material claim, stated only with the
verbatim error, the documented statement, or a live probe in hand —
pattern-matching a failure to a familiar story is not evidence, and a cheap
probe runs BEFORE asking the user or declaring a step blocked. ONE directive
adapted into the preamble resolver; the fork's full judgment contract is
deliberately not imported. Full regen (46 files), ship goldens refreshed,
parity guards bumped with the measured ~0.45KB/skill (investigate, autoplan,
plan-design-review, office-hours), Step 0.9 registered as an intentional
sub-step.

Approved deferrals filed: persona-fleet hostile-user harness + answer-key
methodology in TODOS; the fork's question-budget ACCOUNTING judgment (never
its 5/8/12 constants) folded into the V1.1 pacing design doc; the Apple
adapter added to #1882's coverage note.

Ported from time-attack/gstack (GStack 2).

Co-authored-by: Sina Matian <sina@time-attack.dev>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-08-14 13:30:21 -07:00
parent 15d1144fea
commit 81a2d48592
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
55 changed files with 326 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
TODOS.md
View File

@ -2,6 +2,45 @@
## NEXT PRIORITY
### P2: Persona-fleet hostile-user harness (fork port wave 2 deferral)
**What:** Port the methodology behind time-attack/gstack's 87-hostile-user
field run (418 findings): machine-written t0 in an append-only run.jsonl
(elapsed time measured, never self-reported), every metric resolving to an
artifact, and a mandatory-quit contract with machine-checkable caps (300s to
first useful output, 900s total, 40K context tokens, 3 consecutive dead ends)
so abandonment is a computable outcome. Specs: fork `evals/fleet/METRICS.md`
+ `evals/fleet/ABANDONMENT.md` (methodology only — no runner code exists to
port; this is a build).
**Why:** A periodic hostile-user round against OUR 44-skill tree would surface
the same first-five-minutes failure class the fork closed 418 of. Fits the
existing eval-store/e2e harness as a new runner.
**Effort:** L (human ~2wk) → M with CC. **Priority:** P2.
**Depends on:** decisions on cost ceilings + journal storage.
### P3: Answer-key eval methodology (rides the persona-fleet work)
**What:** Pre-registered answer keys (fork `evals/answer-keys/` —
codex-decorrelation, health-trending) grading our /codex and /health surfaces
against planted ground truth instead of judge vibes.
**Why:** Deterministic scoring for surfaces where LLM-judge drift is the
known failure mode. **Effort:** M → S with CC. **Priority:** P3.
**Depends on:** persona-fleet harness (shared runner shape).
### P3: Quarterly Apple-journey live re-verification
**What:** Run the /ship Apple release adapter against a real (TestFlight-only)
release once a quarter, or on first user bug report, and fix drift. Apple's
APIs move (the fork caught fastlane price_tier breaking live); the adapter's
claims are evidence-backed today and must stay that way per its own
evidence-before-claimed-limitations rule.
**Effort:** S per run. **Priority:** P3. **Depends on:** a paid ADP account.
### P1: #1882 — portable skill-install prefix (non-`gstack` install dirs break silently)
**What:** Every generated SKILL.md hardcodes the literal `~/.claude/skills/gstack/...`
@ -25,6 +64,9 @@ So #1882 is now purely the body-preamble portability work.
invocation-time failures.
**Cons:** Touches the most load-bearing bash in the repo (every skill's preamble);
a silent mistake breaks all 52 skills. High blast radius — needs its own focused PR.
**Note (fork port wave 2):** the Apple release adapter (ship/sections/
apple-release.md) added template surface with `~/.claude/skills/gstack/bin`
references — include it in this fix's coverage list.
**Context / where to start:**
- Rewire `ctx.paths.binDir` (and browse/design dir paths) + the ~9 resolvers that

4
autoplan/SKILL.md
View File

@ -678,6 +678,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
canary/SKILL.md
View File

@ -670,6 +670,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
codex/SKILL.md
View File

@ -673,6 +673,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
context-restore/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
context-save/SKILL.md
View File

@ -673,6 +673,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
cso/SKILL.md
View File

@ -676,6 +676,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
design-consultation/SKILL.md
View File

@ -696,6 +696,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
design-html/SKILL.md
View File

@ -677,6 +677,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
design-review/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
design-shotgun/SKILL.md
View File

@ -691,6 +691,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
devex-review/SKILL.md
View File

@ -676,6 +676,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
diagram/SKILL.md
View File

@ -671,6 +671,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

14
docs/designs/PACING_UPDATES_V0.md
View File

@ -93,3 +93,17 @@ V2 items remain deferred:
- Per-skill or per-topic explain levels
- Team profiles
- AST-based "delivered features" metric
## Fold-in from fork port wave 2 (2026-08-14)
The time-attack/gstack fork attacked the same question fatigue from a
complementary axis: build-scale classification (session/hobby/project/
product/venture) sizing the machinery, plus CHAIN-WIDE question budgets.
Approved decision (CEO review 2026-08-14): fold the fork's ACCOUNTING
judgment into this design round — the budget is chain-scoped (a chained
review deducts from what's left, never resets), handoffs carry
questions-already-spent, approval/mutation gates never count against it, and
the budget is spent on the hardest-to-reverse decisions first. Do NOT adopt
the fork's 5/8/12 numeric constants — the fork itself later replaced them
with a zero-default autonomy dial. Scale sizes the machinery and sets the
budget; pacing (this doc) ranks what the budget is spent on.

4
document-generate/SKILL.md
View File

@ -676,6 +676,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
document-release/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
health/SKILL.md
View File

@ -672,6 +672,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
investigate/SKILL.md
View File

@ -711,6 +711,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ios-clean/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ios-design-review/SKILL.md
View File

@ -676,6 +676,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ios-fix/SKILL.md
View File

@ -677,6 +677,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ios-qa/SKILL.md
View File

@ -680,6 +680,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ios-sync/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
land-and-deploy/SKILL.md
View File

@ -669,6 +669,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
landing-report/SKILL.md
View File

@ -670,6 +670,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
learn/SKILL.md
View File

@ -672,6 +672,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
office-hours/SKILL.md
View File

@ -707,6 +707,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
open-gstack-browser/SKILL.md
View File

@ -669,6 +669,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
pair-agent/SKILL.md
View File

@ -671,6 +671,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
plan-ceo-review/SKILL.md
View File

@ -701,6 +701,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
plan-design-review/SKILL.md
View File

@ -673,6 +673,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
plan-devex-review/SKILL.md
View File

@ -679,6 +679,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
plan-eng-review/SKILL.md
View File

@ -677,6 +677,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
plan-tune/SKILL.md
View File

@ -682,6 +682,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
qa-only/SKILL.md
View File

@ -672,6 +672,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
qa/SKILL.md
View File

@ -678,6 +678,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
retro/SKILL.md
View File

@ -689,6 +689,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
review/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
scrape/SKILL.md
View File

@ -670,6 +670,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

2
scripts/resolvers/preamble.ts
View File

@ -53,6 +53,7 @@ import { generateAskUserFormat } from './preamble/generate-ask-user-format';
import { generateWritingStyle } from './preamble/generate-writing-style';
import { generateCompletenessSection } from './preamble/generate-completeness-section';
import { generateConfusionProtocol } from './preamble/generate-confusion-protocol';
import { generateEvidenceDirective } from './preamble/generate-evidence-directive';
import { generateContinuousCheckpoint } from './preamble/generate-continuous-checkpoint';
import { generateContextHealth } from './preamble/generate-context-health';
@ -113,6 +114,7 @@ export function generatePreamble(ctx: TemplateContext): string {
generateWritingStyle(ctx),
generateCompletenessSection(ctx),
generateConfusionProtocol(ctx),
generateEvidenceDirective(ctx),
generateContinuousCheckpoint(),
generateContextHealth(ctx),
generateQuestionTuning(ctx),

18
scripts/resolvers/preamble/generate-evidence-directive.ts Normal file
View File

@ -0,0 +1,18 @@
import type { TemplateContext } from '../types';
/**
* Evidence-before-claimed-limitations (fork port wave 2, D1).
*
* The single highest-leverage judgment clause from the fork's live App Store
* releases: nine release failures in two days shared one root — the agent
* asserting folklore as fact ("the API can't do this", "X requires a
* password") instead of running the ten-second check that would have
* disproven it. Adapted as ONE directive into the shared preamble (the
* fork's full SHARED-JUDGMENT contract is deliberately not imported).
*/
export function generateEvidenceDirective(ctx?: TemplateContext): string {
if (ctx?.explainLevel === 'terse') return '';
return `## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.`;
}

4
setup-deploy/SKILL.md
View File

@ -673,6 +673,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
setup-gbrain/SKILL.md
View File

@ -672,6 +672,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
ship/SKILL.md
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

19
ship/sections/plan-completion.md
View File

@ -201,16 +201,23 @@ Using the plan file already discovered in Step 8, look for a verification sectio
### 2. Check for running dev server
Before invoking browse-based verification, check if a dev server is reachable:
Before invoking browse-based verification, find the dev-server URL the way the
project declares it — never trust a hardcoded port list alone:
1. **CLAUDE.md first:** look for a documented dev URL or dev command (a
`## Development`/`## Testing` section naming a port or URL). Use it.
2. **The plan file:** if the plan's verification section names a URL, use it.
3. **Fallback probe** (common ports, only when 1-2 found nothing):
```bash
curl -s -o /dev/null -w '%{http_code}' http://localhost:3000 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:8080 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:5173 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:4000 2>/dev/null || echo "NO_SERVER"
for _p in 3000 8080 5173 4000 4321 8000; do
_code=$(curl -s -o /dev/null -w '%{http_code}' "http://localhost:$_p" 2>/dev/null)
[ -n "$_code" ] && [ "$_code" != "000" ] && { echo "DEV_SERVER: http://localhost:$_p ($_code)"; break; }
done
[ -z "${_code:-}" ] || [ "${_code:-000}" = "000" ] && echo "NO_SERVER"
```
**If NO_SERVER:** Skip with "No dev server detected — skipping plan verification. Run /qa separately after deploying."
**If NO_SERVER:** Skip with "No dev server detected (checked CLAUDE.md, the plan, and common ports) — skipping plan verification. Run /qa separately after deploying, or document the dev URL in CLAUDE.md so this step finds it next time."
### 3. Invoke /qa-only inline

4
skillify/SKILL.md
View File

@ -670,6 +670,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

8
spec/SKILL.md
View File

@ -671,6 +671,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.
@ -1755,6 +1759,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
sync-gbrain/SKILL.md
View File

@ -672,6 +672,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

4
test/fixtures/golden/claude-ship-SKILL.md vendored
View File

@ -674,6 +674,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.

23
test/fixtures/golden/codex-ship-SKILL.md vendored
View File

@ -660,6 +660,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.
@ -1872,16 +1876,23 @@ Using the plan file already discovered in Step 8, look for a verification sectio
### 2. Check for running dev server
Before invoking browse-based verification, check if a dev server is reachable:
Before invoking browse-based verification, find the dev-server URL the way the
project declares it — never trust a hardcoded port list alone:
1. **CLAUDE.md first:** look for a documented dev URL or dev command (a
`## Development`/`## Testing` section naming a port or URL). Use it.
2. **The plan file:** if the plan's verification section names a URL, use it.
3. **Fallback probe** (common ports, only when 1-2 found nothing):
```bash
curl -s -o /dev/null -w '%{http_code}' http://localhost:3000 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:8080 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:5173 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:4000 2>/dev/null || echo "NO_SERVER"
for _p in 3000 8080 5173 4000 4321 8000; do
_code=$(curl -s -o /dev/null -w '%{http_code}' "http://localhost:$_p" 2>/dev/null)
[ -n "$_code" ] && [ "$_code" != "000" ] && { echo "DEV_SERVER: http://localhost:$_p ($_code)"; break; }
done
[ -z "${_code:-}" ] || [ "${_code:-000}" = "000" ] && echo "NO_SERVER"
```
**If NO_SERVER:** Skip with "No dev server detected — skipping plan verification. Run /qa separately after deploying."
**If NO_SERVER:** Skip with "No dev server detected (checked CLAUDE.md, the plan, and common ports) — skipping plan verification. Run /qa separately after deploying, or document the dev URL in CLAUDE.md so this step finds it next time."
### 3. Invoke /qa-only inline

23
test/fixtures/golden/factory-ship-SKILL.md vendored
View File

@ -662,6 +662,10 @@ When options differ in coverage, include `Completeness: X/10` (10 = all edge cas
For high-stakes ambiguity (architecture, data model, destructive scope, missing context), STOP. Name it in one sentence, present 2-3 options with tradeoffs, and ask. Do not use for routine coding or obvious changes.
## Claimed Limitations Need Evidence
A claimed limitation or requirement ("the API can't do this", "X requires a credential", "that's impossible on this platform") is a material claim. State one only with the verbatim error, the documented statement, or a live probe in hand — pattern-matching a failure to a familiar story is not evidence. When a cheap probe settles the question, run it BEFORE asking the user anything or declaring a step blocked.
## Continuous Checkpoint Mode
If `CHECKPOINT_MODE` is `"continuous"`: auto-commit completed logical units with `WIP:` prefix.
@ -1874,16 +1878,23 @@ Using the plan file already discovered in Step 8, look for a verification sectio
### 2. Check for running dev server
Before invoking browse-based verification, check if a dev server is reachable:
Before invoking browse-based verification, find the dev-server URL the way the
project declares it — never trust a hardcoded port list alone:
1. **CLAUDE.md first:** look for a documented dev URL or dev command (a
`## Development`/`## Testing` section naming a port or URL). Use it.
2. **The plan file:** if the plan's verification section names a URL, use it.
3. **Fallback probe** (common ports, only when 1-2 found nothing):
```bash
curl -s -o /dev/null -w '%{http_code}' http://localhost:3000 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:8080 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:5173 2>/dev/null || \
curl -s -o /dev/null -w '%{http_code}' http://localhost:4000 2>/dev/null || echo "NO_SERVER"
for _p in 3000 8080 5173 4000 4321 8000; do
_code=$(curl -s -o /dev/null -w '%{http_code}' "http://localhost:$_p" 2>/dev/null)
[ -n "$_code" ] && [ "$_code" != "000" ] && { echo "DEV_SERVER: http://localhost:$_p ($_code)"; break; }
done
[ -z "${_code:-}" ] || [ "${_code:-000}" = "000" ] && echo "NO_SERVER"
```
**If NO_SERVER:** Skip with "No dev server detected — skipping plan verification. Run /qa separately after deploying."
**If NO_SERVER:** Skip with "No dev server detected (checked CLAUDE.md, the plan, and common ports) — skipping plan verification. Run /qa separately after deploying, or document the dev URL in CLAUDE.md so this step finds it next time."
### 3. Invoke /qa-only inline

7
test/gen-skill-docs.test.ts
View File

@ -1050,8 +1050,11 @@ describe('PLAN_VERIFICATION_EXEC placeholder', () => {
expect(shipSkill).toContain('qa-only');
});
test('contains localhost reachability check', () => {
expect(shipSkill).toContain('localhost:3000');
test('contains dev-server discovery (CLAUDE.md first, then a port probe)', () => {
// Fork port wave 2: the hardcoded 4-port list became read-CLAUDE.md-or-
// probe; the probe loops common ports instead of naming each once.
expect(shipSkill).toContain('CLAUDE.md first');
expect(shipSkill).toContain('http://localhost:$_p');
expect(shipSkill).toContain('NO_SERVER');
});

12
test/helpers/carve-guards.ts
View File

@ -208,10 +208,12 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// always-loaded AskUserQuestion Format section.
// v1.2.0 activation lift (shared first-run-guidance preamble) + #2077 ask-first scope gate.
// +~1.3 KB: plan-mode auto-select-B scope-gate exceptions (2026-08).
maxSkeletonBytes: 89_000,
// Fork port wave 2 (D1): evidence directive adds ~0.45KB to every
// tier-2+ skeleton. Measured 89,184.
maxSkeletonBytes: 91_000,
minUnionBytes: 70_000,
mustContain: ['design', 'visual'],
maxSizeRatio: 1.07,
maxSizeRatio: 1.12, // D1 measured 1.104
},
'plan-devex-review': {
skill: 'plan-devex-review',
@ -255,12 +257,12 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// plus the P1 office-hours closing handoff (AUQ that launches the next skill).
// Fork port wave 2: the third-party web-actions contract sits inline
// (judgment must be visible before the workflow directs the user to a
// vendor site), plus the #703 dual-write + repo-doc-preference block —
// ratio 1.092 measured. Tight headroom.
// vendor site), plus the #703 dual-write + repo-doc-preference block and
// the #538 opt-out + D1 evidence directive — ratio 1.104 measured.
maxSkeletonBytes: 101_000,
minUnionBytes: 70_000,
mustContain: ['design doc', 'problem statement'],
maxSizeRatio: 1.10,
maxSizeRatio: 1.12,
},
'document-release': {
skill: 'document-release',

8
test/helpers/parity-harness.ts
View File

@ -240,7 +240,9 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
// 1.09 → 1.10: the plan-mode preamble reword (scope-gate auto-select-B
// change) adds ~250 B to every skill's shared preamble; investigate was
// the closest to its ceiling (landed 1.092).
maxSizeRatio: 1.10,
// Fork port wave 2 (D1): the evidence-before-claimed-limitations preamble
// directive adds ~0.45KB to every tier-2+ skill. Measured values noted.
maxSizeRatio: 1.12, // D1 measured
minBytes: 30_000,
},
{
@ -248,7 +250,9 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
mustContain: ['ceo', 'eng', 'design'],
mustHaveHeadings: ['## Preamble', '## When to invoke'],
// v1.2.0 activation lift: shared first-run-guidance preamble section.
maxSizeRatio: 1.07,
// Fork port wave 2 (D1): the evidence-before-claimed-limitations preamble
// directive adds ~0.45KB to every tier-2+ skill. Measured values noted.
maxSizeRatio: 1.09, // D1 measured
minBytes: 70_000,
},
];

8
test/skill-validation.test.ts
View File

@ -1216,9 +1216,11 @@ describe('Step 3.4 test coverage audit', () => {
describe('ship step numbering', () => {
// Allowed sub-steps that are resolver-generated and intentionally nested:
// 8.1 (Plan Verification), 8.2 (Scope Drift), 9.1 (Review Army), 9.2 (Findings Merge),
// 9.3 (Cross-review dedup), 15.0 (WIP squash — continuous checkpoint), 15.1 (Bisectable commits).
const ALLOWED_SUBSTEPS = new Set(['8.1', '8.2', '9.1', '9.2', '9.3', '15.0', '15.1']);
// 0.9 (Apple target detection — MUST precede Step 1's branch gate, R2-pinned
// by test/ship-apple-gate.test.ts), 8.1 (Plan Verification), 8.2 (Scope
// Drift), 9.1 (Review Army), 9.2 (Findings Merge), 9.3 (Cross-review dedup),
// 15.0 (WIP squash — continuous checkpoint), 15.1 (Bisectable commits).
const ALLOWED_SUBSTEPS = new Set(['0.9', '8.1', '8.2', '9.1', '9.2', '9.3', '15.0', '15.1']);
test('ship/SKILL.md.tmpl contains no unexpected fractional step numbers', () => {
const tmpl = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md.tmpl'), 'utf-8');