Give two recurring prompt-conformance classes their mechanical rung

.github/workflows/ci.yml

@@ -73,14 +73,15 @@ jobs:
       - name: Hook state-machine tests
         run: sh plugins/dev-workflow/hooks/codex-gate.test.sh
 
-      # Invariants 5 and 6 mechanically, plus BOTH checkers' regression suites. The
+      # Invariants 5 and 6 plus two prompt-conformance checks, mechanically, and BOTH
+      # checkers' regression suites. The
       # invariant-12 checker itself is not here — it needs a PR base and runs in the
       # step below, so naming this step "version bump" would show a green version-bump
       # label on a push that was never version-bump checked.
       # Each rule was prose first and each was violated anyway — a floating action ref
       # shipped in this very workflow, a duplicate hooks manifest key stopped the plugin
       # loading in 0.2.1, and the plugin shipped changes without a bump twice.
-      - name: Invariant checks (pinning, manifest) + both checker suites
+      - name: Invariant checks (pinning, manifest, prompt conformance) + both checker suites
         run: |
           sh scripts/check-invariants.test.sh
           sh scripts/check-invariants.sh

AGENTS.md

@@ -34,7 +34,7 @@ todos.md                          # backlog; `pending` ledger rows point here by
 .mcp.json                         # the Codex reviewer, pinned
 .claude-plugin/marketplace.json
 .github/workflows/ci.yml          # lint + hook tests + invariant checks + validate
-scripts/check-invariants.sh       # invariants 5 and 6, mechanically (rung 2)
+scripts/check-invariants.sh       # invariants 5, 6 + prompt conformance (rung 2)
 scripts/check-invariants.test.sh  # its regression suite — reject/accept pairs
 scripts/check-version-bump.sh     # invariant 12, mechanically — PR-only (rung 2)
 scripts/check-version-bump.test.sh # its regression suite — policy/operational/accept
@@ -167,8 +167,12 @@ reader can judge whether it still holds.
     `docs/hardening-taxonomy.md`, never into the `harden-finding` skill. Otherwise one
     project leaks into every other.
 11. **Prompt changes pass `docs/prompt-standards.md`** — all 12 checklist items, for
-    any skill, command, agent definition, hook message, or scaffolded template. The prompts are the
-    product and nothing mechanical checks them.
+    any skill, command, agent definition, hook message, or scaffolded template. The
+    prompts are the product, and **no comprehensive mechanical checker exists for them**:
+    review is the gate. Two narrow checks in `scripts/check-invariants.sh` cover one
+    spelling each — a `Target model:` line naming exactly one recognized model in files
+    claiming conformance, and a prose checklist-count claim matching the checklist — and
+    they are a floor, not coverage. Every other item is judged by a reader.
 
 ## Don'ts
 
@@ -231,7 +235,7 @@ Every command below was run in this session and observed to exit 0.
 | typecheck | n/a — no typed sources (shell + markdown) |
 | lint | `shellcheck --shell=sh plugins/dev-workflow/hooks/codex-gate.sh && shellcheck --shell=sh --exclude=SC2015 plugins/dev-workflow/hooks/codex-gate.test.sh && shellcheck --shell=sh scripts/check-invariants.sh && shellcheck --shell=sh --exclude=SC2015 scripts/check-invariants.test.sh && shellcheck --shell=sh scripts/check-version-bump.sh && shellcheck --shell=sh scripts/check-version-bump.test.sh` |
 | test | `sh plugins/dev-workflow/hooks/codex-gate.test.sh` |
-| invariant checks (5 pinning, 6 manifest) | `sh scripts/check-invariants.test.sh && sh scripts/check-invariants.sh` |
+| invariant checks (5 pinning, 6 manifest, prompt conformance) | `sh scripts/check-invariants.test.sh && sh scripts/check-invariants.sh` |
 | invariant check (12 version bump) | `sh scripts/check-version-bump.test.sh && sh scripts/check-version-bump.sh main` |
 | build | n/a — nothing is compiled or bundled |
 

README.md

@@ -123,7 +123,7 @@ honest gap ([reasoning](docs/coding-workflow.md#adapting-it-to-another-project))
 CI ([`.github/workflows/ci.yml`](.github/workflows/ci.yml)) runs four checks on every
 PR and push to main: `shellcheck --shell=sh` over all three executables and their test
 files, the hook's test suite,
-[`scripts/check-invariants.sh`](scripts/check-invariants.sh) (invariants 5 and 6) plus
+[`scripts/check-invariants.sh`](scripts/check-invariants.sh) (invariants 5 and 6, plus two prompt-conformance checks) plus
 both checkers' regression suites, and `claude plugin validate . --strict`.
 
 A fifth check runs **on pull requests only**:

docs/architecture.md

@@ -15,7 +15,7 @@ README.md, MANIFEST.md, AGENTS.md, CLAUDE.md, todos.md
 .mcp.json                         # the Codex reviewer, pinned
 .claude-plugin/marketplace.json
 .github/workflows/ci.yml          # lint + hook tests + invariant checks + validate
-scripts/check-invariants.sh       # invariants 5 and 6, mechanically (+ .test.sh)
+scripts/check-invariants.sh       # invariants 5, 6 + prompt conformance (+ .test.sh)
 scripts/check-version-bump.sh     # invariant 12, PR-only, mechanically (+ .test.sh)
 plugins/dev-workflow/
   .claude-plugin/plugin.json

docs/hardening-log.md

@@ -26,3 +26,5 @@ escape `\|`, one line), `source` (gate-a|gate-b|bot|manual),
 | 2026-07-20 | truncated-tool-output-read-as-complete | Codex Gate A responses arrived cut off on long finding lists — on effectively every substantial pass in real project use — and a cut landing between findings is indistinguishable from a short list, so dropped findings read as a clean review; field agents were improvising a write-to-file workaround per session, which means the failure was handled only when someone happened to notice | manual | major | P std | CLAUDE.md §5 "Findings go to a FILE, not the response" + the same block in the workflow-init inline template: Codex writes the full list to `.context/codex-reviews/<slot>.md` ending `END OF FINDINGS (<n> total)`, replies with one line, and the reader accepts only on terminator-present AND count-matching AND nothing-but-finding-lines AND (for Gate-B `full`) both branch files. Gate B needs one file per branch because `reviewType: full` runs two reviewers in parallel off one additionalContext — a shared path lets the second overwrite the first and still pass every check. What it does NOT do: nothing checks the terminator mechanically (instruction-backed by design; a recurrence is the trigger to build the checker); the hook counts on `PostToolUse` and never sees the file, so an incomplete pass still increments the counter — including a FAILED review, because the pinned `mcp-codex-dev@1.0.1` catches its own errors, executor timeouts and aborts included, and returns `{success: false}` as a normal result rather than throwing, so Claude Code reads it as a successful tool call (an earlier draft of this row inferred from the documented `PostToolUseFailure` split that errors increment nothing — Gate B caught it by reading the server; the rule is now stated without reference to event routing: discount every incomplete pass whatever the counter says); and detection misses a model writing a wrong count with matching lines, or a stale file if the pre-call delete is skipped. Secondary mitigation only, in README: `MAX_MCP_OUTPUT_TOKENS` (25,000 default) moves the ceiling, does not remove it, and does not apply to tools declaring `anthropic/maxResultSizeChars`. Which documented mechanism (token limit vs persist-to-disk threshold) caused the field loss was NOT established; the protocol is correct under either. Fingerprint minted rather than filed under `verification-masks-failure`: that would make this a recurrence on a `1 prose` row, and the skill's recurrence rule then demands a mechanical rung or sharpened AGENTS.md wording, neither of which is P — three Gate-A passes each rejected a different attempt to narrate that gap, which is the class being bent to fit the ladder rather than the defect |
 | 2026-07-25 | docs-drift | docs/prompt-standards.md said ad-hoc briefs are not reviewed against "all ten items" while its own checklist runs 1-12 and AGENTS.md invariant 11 independently says 12 — a hard-coded count contradicting the list it counts, in the same file | bot | minor | pending | todos.md § Tooling revalidation, "Prompt-standards conformance checker — resolves two `pending` ledger rows (2026-07-25)". THIRD occurrence of this class, after 2026-07-18 `1 prose` (manifest-claims rule) and 2026-07-18 `P std` (spec-updated-with-fix rule); neither prior rung could reach a stale count, and the ladder's escalation from those is mechanical. The FIX landed in 4f31df2 (PR #12) — what is pending is the HARDENING, not the defect. Deferred by explicit decision: the checker is ~8 lines of shell plus tests, and writing it into a docs-only PR would fire full Gate B on new shell code; it rides the upcoming canvas-findings hardening round instead, which pays that cost anyway. Resolve by appending a rung-2 row referencing this one, never by editing it |
 | 2026-07-25 | unverified-enforcement-claim | docs/sparring-briefing.md asserted "This is a prompt artifact and follows docs/prompt-standards.md" while giving its target model as "any capable chat model" — checklist item 1 requires a NAMED executing model plus the author having checked that model's prompting page, and a model class satisfies neither half (there is no single page to check), so the document contradicted its own conformance claim | bot | major | pending | todos.md § Tooling revalidation, "Prompt-standards conformance checker — resolves two `pending` ledger rows (2026-07-25)". THIRD occurrence, after 2026-07-18 `P std` (prompt-standards item 11) and 2026-07-19 `1 prose` (the "never describe what a gate proves" rule, whose own ref states it is human-run, not CI-run, and "raises the floor; it does not close the class"). The class has now cycled P std → 1 prose → recurrence without ever reaching a deterministic rung, and this instance IS tool-decidable — a file claiming to follow prompt-standards must carry a `Target model:` line — which is why the escalation is mechanical rather than a fourth prose rule. The FIX landed in 4f31df2 (PR #12); the HARDENING is what is pending, deferred to the canvas-findings round on the same scope reasoning as the sibling row. Resolve by appending a rung-2 row referencing this one, never by editing it |
+| 2026-07-26 | unverified-enforcement-claim | third occurrence, resolved: a prompt asserting it follows docs/prompt-standards.md while naming no executing model — the PR #12 sparring-briefing said `Target model: any capable chat model` | bot | major | 2 lint | scripts/check-invariants.sh check 4a + fixtures in .test.sh. **Resolves the 2026-07-25 `pending` row** (same fingerprint, appended not edited). GUARDED SPELLING, exactly: in a `*.md` file containing the literal `prompt artifact and follows`, the column-zero `^Target model:` line must appear exactly once, its value must BEGIN with a tested token (`Claude\|Codex\|GPT`, portable ERE boundary — token-anywhere is not enough, since the real defect line contained "Claude" as provenance), and it must name exactly one DISTINCT token. STILL INSTRUCTION-BACKED: a bare `Target model: Claude` naming no execution surface passes; a value whose prose is wrong in a way no token test sees passes; a column-zero declaration inside a fenced block counts (no fence awareness in POSIX grep); an unknown future model fails until the token list is extended. BLIND SPOT, stated because it is structural: this ledger is EXCLUDED from the check it records — a ledger that quotes defects self-rejects the checks that detect them, and scanning it would fail the repo forever on rows like this one. OVER-ESCALATION WARNING: `harden-finding` compares fingerprints only, so a later in-class defect OUTSIDE the guarded spelling will be proposed for a stronger rung than anything justifies; that is a proposal a human validates, and this row names the guard so they can judge it. The skill's scope-blind recurrence rule is parked in todos.md |
+| 2026-07-26 | docs-drift | third occurrence, resolved: a prose count contradicting the checklist it counts — PR #12's `docs/prompt-standards.md` said "all ten items" while its own checklist ran 1-12 | bot | minor | 2 lint | scripts/check-invariants.sh check 4b + fixtures in .test.sh. **Resolves the 2026-07-25 `pending` row** (same fingerprint, appended not edited). GUARDED SPELLING, exactly: two-stage claim recognition over `*.md` — stage 1 matches `all <digits\|one..twenty>( checklist)? items` with outer word boundaries, stage 2 requires canonical decimal, so `all 012 items` fires as malformed rather than being invisible; every recognised claim must equal N, where N comes from exactly one `^## Checklist([[:space:]].*)?$` heading whose body holds labels forming the contiguous canonical sequence 1..N, in BOTH docs/prompt-standards.md and the workflow-init template, which must agree. Word forms are in scope BECAUSE the motivating occurrence was one — a digit-only check would have sailed past the very defect this row claims to harden. STILL INSTRUCTION-BACKED: counts above twenty in word form, ordinals, hyphenated compounds (`all twenty-one items`), split-line claims, and any count of something other than this checklist. Same ledger blind spot and over-escalation warning as the row above |