[CAT-UNVERIFIED tag](6) show-me-your-work names the tag, and guard the whole repo

[EdbertChan]

Summary

show-me-your-work now tells the author to mark a same-model review with the tag, blocker named.

It told authors to use bare UNVERIFIED:, which the hooks now reject.

That was the last such line, so a repo-wide test now fails on any rule, skill or hook README that brings it back.

Review Claim

Approve show-me-your-work naming the tag, and a test that fails when any instructional file tells an author to write bare UNVERIFIED:.

Review Lane

behavior

Review Unit

product-skill

Safety Invariant

Prose plus a read-only repo scan test; no runtime change.

Slice Rationale

Product skills are their own review unit. The repo-wide guard lands here, last, because this is the first point where every line it scans is migrated.

Non-goals

No hook, script or install change.

Test Plan

Test Plan

• python3 engine/skills/make-pr/scripts/preflight.py --base <this PR's base>

unit    product-skill: 1 file(s)
neutral 2 file(s): tests/test_escape_hatch_vocabulary.py, tests/test_show_me_your_work.py
declare Review Unit: product-skill
gate    python3 scripts/check_codify_has_code.py --base stack/EdbertChan/cat-unverified-tag/5-docs
        ok      codify-has-code
gate    python3 scripts/check_no_dated_provenance.py --base stack/EdbertChan/cat-unverified-tag/5-docs
        ok      no dated provenance
gate    python3 scripts/check_skills_three_harnesses.py
        ok      skills three-harness check
gate    python3 scripts/check_ecosystem_boundaries.py
        ok      ecosystem boundaries
gate    python3 scripts/check_skill_file_refs.py
        ok      skill file refs
gate    python3 scripts/check_skill_test_coverage.py --base stack/EdbertChan/cat-unverified-tag/5-docs --head HEAD
        ok      skill test coverage
gate    python3 scripts/check_skill_trigger_mechanism.py
        ok      skill trigger mechanism
gate    python3 scripts/check_skill_trigger_policy.py
        ok	skill trigger policy
gate    python3 scripts/check_subagent_scope_contract.py
        ok	subagent scope contract
gate    python3 scripts/run_skill_scenarios.py
        ok  	subagent-fact-attributed
        ok  	stale-green-caught-without-any-admission
        ok  	stale-green-already-owned-by-the-reply
        ok  	red-then-green-is-a-fix-not-a-stale-claim
        
        ok	all 19 scenario(s) behaved as declared
ok      preflight passed

• bash scripts/run_all_tests.sh -- exit 0, 45 suites OK, 0 failed, 1684 tests
• tests/test_escape_hatch_vocabulary.py -- the scan flags 30 instructing lines on 509b9cd and 0 here

Revert Plan

Revert Plan

• Safe to revert? Yes
• Revert command: git revert <sha>
• Post-revert steps: None
• Data migration? No

🤖 Generated with Claude Code

https://claude.ai/code/session_01VKsvxJk65w6q7KnPSRYvNg

---

Note

Low Risk
Documentation and read-only test coverage only; no hook, install, or runtime behavior changes.

Overview
show-me-your-work no longer tells authors to prefix the Attention line with bare UNVERIFIED: when same-model self-review is unavoidable. It now names the full {{CAT-UNVERIFIED: the review -- cannot verify: same-model self-review}} tag so the skill matches evidence hooks that only clear on that form.

A new tests/test_escape_hatch_vocabulary.py suite walks instructional rules/skills/READMEs via escape_hatch_vocab, failing if any file still instructs writers to use the retired bare marker (while allowing mentions that it is retired, the tag itself, and incidental “UNVERIFIED” wording). test_show_me_your_work.py adds a focused check that the skill text passes that detector and contains the new tag string.

^{Reviewed by Cursor Bugbot for commit 9a89783. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_8826b7f2-7d46-4e7f-bd6c-8519ea5f9d9c)

[EdbertChan]

Mergify repair stopped: lowest open stack PR #420 is based on stack/EdbertChan/cat-unverified-tag/5-docs, which still belongs to open PR(s) #419 outside this stack; leaving it alone to avoid dropping dependency changes

[cursor]

Bugbot couldn't run - usage limit reached

Bugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit.

A user or team admin can review and increase usage limits in the Cursor dashboard.

(requestId: serverGenReqId_3ef7bc06-edbd-474c-a57b-bac332407433)

[mergify]

Tick the box to add this pull request to the merge queue (same as @mergifyio queue).

• Queue this pull request