cat-mode: show the escape-hatch tag in the form the gate accepts by EdbertChan · Pull Request #786 · EdbertChan/catstack

EdbertChan · 2026-09-22T14:31:12Z

Summary

The conventions file shows the escape-hatch tag in a bare form the gate rejects.

Anyone quoting that line verbatim, which the same file tells them to do when relaying a blocked message, trips the gate.

This puts the full template in that line, matching how the core rules file already writes it.

Review Claim

The conventions file shows the tag in the form the gate accepts.

Review Lane

behavior

Review Unit

corpus-lesson

Safety Invariant

Only the example text changes. The gate's own rules are untouched, so nothing that used to block stops blocking.

Slice Rationale

A one-line documentation fix with a test that pins it. Kept out of the gate change so a prose edit never rides along with behaviour.

Non-goals

Does not change the tag format itself or any gate logic.

Test Plan

Run at this commit:

python3 tests/test_cat_mode.py
Ran 87 tests in 0.048s
OK

The added case asserts every tag example in the conventions file is one the gate accepts.

Revert Plan

Revert this commit. The example returns to the bare form and quoting it trips the gate again.

Note

Low Risk
Documentation and regression tests only; marker validation behavior is untouched.

Overview
cat-mode showed the escape-hatch as bare {{CAT-UNVERIFIED}} in the rule that tells readers to use that tag when they cannot prove a live-behavior claim. Quoting that line verbatim tripped the same gate the tag is meant to satisfy.

The one-line rule in SKILL.md and the fuller copy in references/verify.md now use the full template {{CAT-UNVERIFIED: <claim> -- cannot verify: <reason>}}, aligned with engine/CLAUDE.core.md. Gate logic is unchanged.

tests/test_cat_mode.py adds TestEscapeHatchTemplateIsWellFormed: it scans SKILL.md and every references/*.md via engine/hooks/_markers/markers.py so malformed tag examples cannot slip back in via verify.md alone.

^{Reviewed by Cursor Bugbot for commit 2e69d29. Bugbot is set up for automated code reviews on this repo. Configure here.}

EdbertChan · 2026-09-22T14:31:26Z

This pull request is part of a Mergify stack:

#	Pull Request	Link
1	wrong-check-reflect: one shot per reply, and scope the reflect scan to the turn	#796
2	reflect: catch an evidence-order correction from the ledger transition, not from wording	#782
3	unverified-tag-ledger: gate the next-prompt reminder, default to stale only	#783
4	diu-stop: a file citation buys silence only when it is backed	#784
5	diu-stop: the marker gate reads prose, so a mention is not a use	#785
6	cat-mode: show the escape-hatch tag in the form the gate accepts	#786	👈
7	principle-subagent-inherits-scope: a brief carries decisions, not just facts and a question	#788
8	llm-judge: claude is the only default runner	#793

EdbertChan · 2026-09-22T18:38:39Z

Revision history

#	Type	Changes	Date
1	initial	`0201bdc`	2026-09-22 18:38 UTC
2	rebase	`0201bdc → fab6704` (rebase only)	2026-09-22 18:38 UTC
3	rebase	`fab6704 → 1937775` (rebase only)	2026-09-23 14:06 UTC

cursor

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit fab6704. Configure here.}

EdbertChan · 2026-09-23T20:04:55Z

Mergify repair stopped: lowest open stack PR #786 is based on stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383, which still belongs to open PR(s) #785 outside this stack; leaving it alone to avoid dropping dependency changes

cursor · 2026-09-24T08:30:03Z

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_ea2da72e-fd47-43db-b44d-ed1a0d1ab13b)

cursor · 2026-09-24T10:06:03Z

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_dbe02907-5745-4823-8fe1-3b306668f806)

mergify · 2026-09-24T10:41:16Z

Queued — the merge queue status continues in this comment ↓.

The sentence that tells the reader to use the tag showed it as a bare token naming no blocker. That is the shape diu-stop rejects, so quoting cat-mode's own rule tripped the gate enforcing it. It now shows the same template engine/CLAUDE.core.md already uses. tests/test_cat_mode.py gains the structural catch: no tag anywhere in the skill may name no blocker, and the skill must still show the tag at all, so the fix cannot be "delete the example". Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Change-Id: If47021e83bdf3d8771ccbdb879001f6effc65a3c

The bare `{{CAT-UNVERIFIED}}` was fixed in SKILL.md, but the same sentence lives twice on purpose: SKILL.md keeps the one-line form and references/ verify.md holds the full text the evidence gate leans on. verify.md still showed the tag naming no blocker, so a reader sent to the reference copied the shape diu-stop rejects. verify.md now shows the same template. The structural catch walks every markdown file in the skill instead of SKILL.md alone, and asserts the two files that carry the rule are in the swept list, so an empty or mis-rooted scan cannot report clean. The "still shows the tag at all" assertion now covers both copies, so the fix cannot be deleting the example in either. Fail-before / pass-after on tests.test_cat_mode.TestEscapeHatchTemplateIsWellFormed: the extended scan fails on verify.md's `['{{CAT-UNVERIFIED}}']` before the edit, and the full 91-test tests/test_cat_mode.py suite passes after. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

…#786 Exit code: 0

The escape-hatch test explained why it pins SKILL.md and verify.md by name in three `#` comment lines. Comments are banned in code here, and CI's no-comments twin (scripts/ci/check_no_new_comments.py, the gate for engine/hooks/no-comments) failed the PR on exactly those three lines. The reason is worth keeping: a scan over an empty or mis-rooted list reports clean and reads the same as a pass, so the two files that carry the rule are asserted into the list before the sweep runs. Moving that text into the method docstring keeps it where a reader and `unittest -v` both see it, and the detector only looks for `#` and `//`. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

…est) Exit code: 0

EdbertChan · 2026-09-24T11:08:57Z

@Mergifyio queue

cursor · 2026-09-24T11:09:03Z

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_fd27c241-ea9f-4f63-b0a9-0a7c35fb7a19)

mergify · 2026-09-24T11:09:18Z

queue

🛑 The pull request has been removed from the queue `admin-bypass`

Details

The pull request #786 has been manually updated.

You can take a look at Mergify Merge Queue check runs for more details about the failure.

EdbertChan · 2026-09-24T11:25:26Z

@Mergifyio queue

mergify · 2026-09-24T11:25:31Z

Merge Queue Status

✅ Entered queue — 2026-09-24 11:25 UTC · Rule: admin-bypass · triggered by @EdbertChan with the @mergifyio queue command
✅ Checks passed · on draft merge queue: checking #786 on main (67ace70) #939
✅ Merged — 2026-09-24 11:45 UTC · at c9749395b9d27fd62ebae4150dbddfbf8b5ed309 · squash

This pull request spent 20 minutes 22 seconds in the queue, including 19 minutes 55 seconds running CI.

Required conditions to merge

check-success = lint
check-success = test
check-success = validate

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8 branch from 0201bdc to fab6704 Compare September 22, 2026 18:38

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383 branch from a993989 to a0e5d05 Compare September 22, 2026 18:38

EdbertChan mentioned this pull request Sep 22, 2026

wrong-check-reflect: one shot per reply, and scope the reflect scan to the turn #796

Merged

cursor Bot reviewed Sep 22, 2026

View reviewed changes

Comment thread tests/test_cat_mode.py Outdated

EdbertChan added the admin-bypass label Sep 22, 2026

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383 branch from a0e5d05 to 950a355 Compare September 23, 2026 14:06

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8 branch from fab6704 to 1937775 Compare September 23, 2026 14:06

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383 branch from 950a355 to b0e1eea Compare September 24, 2026 08:29

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8 branch from 3ed5352 to 1fb69a0 Compare September 24, 2026 08:29

EdbertChan mentioned this pull request Sep 24, 2026

admin-bypass-repair-bot-thread-pr-786-1937775 #842

Closed

9 tasks done

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8 branch from 1fb69a0 to a8e7f75 Compare September 24, 2026 10:05

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383 branch from b0e1eea to 51ed95a Compare September 24, 2026 10:05

EdbertChan changed the base branch from stack/EdbertChan/reflect/subagent-decisions-slot-20260922/diu-stop-marker-gate-reads-prose-mention-use--8d19b383 to main September 24, 2026 10:40

CI Bot and others added 4 commits September 24, 2026 19:08

invoker: wf-1790182339789-300/repair — Resolve bot review thread on PR …

aac5c8b

…#786 Exit code: 0

invoker: wf-1790184153761-310/repair — Repair PR #786 (failed check t…

2e69d29

…est) Exit code: 0

EdbertChan force-pushed the stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8 branch from a8e7f75 to 2e69d29 Compare September 24, 2026 11:08

mergify Bot added the queued label Sep 24, 2026

mergify Bot mentioned this pull request Sep 24, 2026

merge queue: checking #786 on main (67ace70) #939

Closed

6 tasks done

mergify Bot merged commit c974939 into main Sep 24, 2026
6 checks passed

mergify Bot removed the queued label Sep 24, 2026

Navigation Menu

cat-mode: show the escape-hatch tag in the form the gate accepts - #786

cat-mode: show the escape-hatch tag in the form the gate accepts#786
mergify[bot] merged 5 commits into
mainfrom
stack/EdbertChan/reflect/subagent-decisions-slot-20260922/cat-mode-show-escape-hatch-tag-form-gate-accepts--f47021e8

EdbertChan commented Sep 22, 2026 •

edited by cursor Bot

Loading

Uh oh!

EdbertChan commented Sep 22, 2026 •

edited

Loading

Uh oh!

EdbertChan commented Sep 22, 2026 •

edited

Loading

Uh oh!

cursor Bot left a comment

Uh oh!

Uh oh!

EdbertChan commented Sep 23, 2026

Uh oh!

cursor Bot commented Sep 24, 2026

Uh oh!

cursor Bot commented Sep 24, 2026

Uh oh!

mergify Bot commented Sep 24, 2026 •

edited

Loading

Uh oh!

EdbertChan commented Sep 24, 2026

Uh oh!

cursor Bot commented Sep 24, 2026

Uh oh!

mergify Bot commented Sep 24, 2026

Uh oh!

EdbertChan commented Sep 24, 2026

Uh oh!

mergify Bot commented Sep 24, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

EdbertChan commented Sep 22, 2026 • edited by cursor Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Review Claim

Review Lane

Review Unit

Safety Invariant

Slice Rationale

Non-goals

Test Plan

Revert Plan

Uh oh!

EdbertChan commented Sep 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

EdbertChan commented Sep 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Revision history

Uh oh!

cursor Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

EdbertChan commented Sep 23, 2026

Uh oh!

cursor Bot commented Sep 24, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

cursor Bot commented Sep 24, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

mergify Bot commented Sep 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

EdbertChan commented Sep 24, 2026

Uh oh!

cursor Bot commented Sep 24, 2026

Bugbot couldn't run - usage limit reached

Uh oh!

mergify Bot commented Sep 24, 2026

🛑 The pull request has been removed from the queue admin-bypass

Uh oh!

EdbertChan commented Sep 24, 2026

Uh oh!

mergify Bot commented Sep 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merge Queue Status

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

EdbertChan commented Sep 22, 2026 •

edited by cursor Bot

Loading

EdbertChan commented Sep 22, 2026 •

edited

Loading

EdbertChan commented Sep 22, 2026 •

edited

Loading

mergify Bot commented Sep 24, 2026 •

edited

Loading

🛑 The pull request has been removed from the queue `admin-bypass`

mergify Bot commented Sep 24, 2026 •

edited

Loading