* Drop frontmatter metadata from the OpenAI copy of the canonical skill
The OpenAI plugin portal rejected the Skills-only ZIP on
skills/avoid-ai-writing/SKILL.md: "Skill interface settings must use
agents/openai.yaml ... `metadata` in SKILL.md does not configure the skill
interface." That copy was byte-identical to root SKILL.md, whose frontmatter
carries an agentskills.io/OpenClaw `metadata` block (author, repository,
tags, agentskills_spec, openclaw.emoji).
- sync-plugin-skill.sh writes the OpenAI copy with the `metadata` block
removed from the frontmatter; everything else stays identical. The Claude
plugin copy is unchanged.
- validate-openai-plugin.py compares root-minus-metadata to the copy for its
drift check and rejects a `metadata` key in any packaged skill's SKILL.md,
so the portal error cannot recur silently.
- validate-openai-plugin.test.py covers the transform (body untouched,
version/license/compatibility kept, no-frontmatter passthrough, copy in
sync) and three red controls: a byte-identical copy fails both rules, a
body edit still reads as drift, and `metadata` in another skill fails.
Verified: validate-openai-plugin.test.py, validate-openai-plugin.py . (OK),
npm test, and the rebuilt archive validates after extraction. The rebuilt
ZIP was accepted by the portal's upload validation.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaeXzpBoBZKa1dWxVS1bTE
* Single-source the metadata strip and correct the exact-copy wording
Codex review of the previous commit found the awk and Python transforms
could diverge (CRLF files, a frontmatter without a closing delimiter, a
missing final newline) and that both ended the metadata block at a blank
line, leaving orphaned nested keys.
- sync-plugin-skill.sh now calls validate-openai-plugin.py
--strip-frontmatter-metadata, so one implementation produces the copy and
checks it.
- strip_frontmatter_metadata keeps line endings byte-exact, treats blank
lines inside the block as part of it, and returns text without a
well-formed frontmatter unchanged; the drift check compares bytes again.
- Tests add the edge inputs from the review and a CLI-vs-function
byte-equality check.
- OPENAI_PLUGIN.md, NOTICE.md, and submission-pack.json no longer call the
bundled copy an exact copy; they state the one omitted block.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaeXzpBoBZKa1dWxVS1bTE
* Match only the top-level metadata key and keep comments inside the block
Codex second pass: `metadata:extra:` is a distinct YAML key and was being
stripped by the prefix match; a column-zero `#` comment inside the metadata
block ended the block early and left an orphaned nested key. The key match
now requires whitespace or end of line after `metadata:`, comment lines
inside the block are skipped with it, and both cases have tests.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaeXzpBoBZKa1dWxVS1bTE
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
* feat: seed OpenAI plugin skill resources
* feat: add OpenAI plugin manifest and public metadata
* feat: add routed ChatGPT and Codex skill graph
* test: add OpenAI plugin validation and submission pack
* fix: correct listing character-count evidence
* feat: add typed cross-skill handoff contract
* docs: encode agency review lenses for orchestration
* feat: add machine-validated typed skill graph
* feat: upgrade router to typed orchestration protocol
* feat: connect detector to typed handoff network
* feat: connect rewriter to verification and representation guards
* feat: add typed file-edit handoffs and repair loop
* feat: make preservation verifier a blocking typed gate
* feat: connect interpretation guardrail to evidence handoffs
* refactor: replace legacy yaml graph with validated json graph
* test: validate skill graph and cross-skill contracts
* ci: validate cross-skill orchestration graph
* refactor: package connection validator inside router skill
* refactor: keep connection validator inside packaged router skill
* ci: run packaged connection validator before and after extraction
* docs: align routing matrix with typed graph
* test: expand routing evals for connected skill graph
* fix: remove unintended reviewer detector cycle
* fix: make interpretation reviewer terminal in skill graph
* test: reject terminal outgoing edges and unbounded graph cycles
* docs: align handoff contract with terminal reviewer semantics
* docs: route fresh interpretation evidence through router
* docs: document graph v2 and connection validation
* fix: route fresh detector requests through orchestrator
* test: enforce agency lenses and router-return semantics
* test: cover terminal reviewer return-to-router flow
* docs: add connected skill graph v2 to release notes
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: remove unsupported skill policy products
* fix: align plugin validator with graph v2 and ingestion policy
* fix: synchronize bundled detector and verifier resources
* fix: bundle detector beside preservation validator
* ci: watch canonical detector resources for plugin drift
* test: smoke packaged preservation residual detector
* ci: exercise residual detector before and after packaging
* fix(port): sync ChatGPT/Codex plugin version with canonical SKILL.md
The merge with main moves the canonical skill to 3.28.0; the plugin
manifest, listing, and submission pack still carried 3.25.1, so
scripts/sync-plugin-skill.sh and scripts/validate-openai-plugin.py both
exit 1 on the effective merge. Bump the three manifests and regenerate
the copies the sync script owns.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): publish the plugin from the canonical repository
Every public destination in the ChatGPT/Codex package pointed at the
contributor's fork: websiteURL, privacyPolicyURL, termsOfServiceURL,
homepage, repository, the submission listing, and SUPPORT.md. After a
merge the canonical owner would not control the published legal and
support pages. Point them all at conorbronsdon/avoid-ai-writing and make
developerName/packagePublisher the identity that will be verified in the
OpenAI portal. Packaging credit stays: NOTICE.md and listing.json now
name the contributor explicitly.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(detector): CRLF input no longer bypasses the preservation validator
validate() extracts frontmatter, tables and headings with regexes that
anchor on a bare newline. A CRLF document matched none of them, so
changing 'title: one' to 'title: two' in Windows-formatted frontmatter
returned { ok: true, errors: [] }. This is a pre-existing bug in the
canonical detector, not something PR #135 introduced - the bundled
plugin copy is byte-identical to detector/validate.js - so the fix and
the must-fire fixtures go in the canonical source and the generated copy
is re-synced from it.
Adds four CRLF fixtures to detector/validate.test.js; all four fail
against the unpatched validator.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): make the manifest the only source for listing metadata
submission/listing.json restates twelve manifest fields and only three
of them were asserted, so the listing could ship a different developer
name, support URL or description than the manifest it claims to
describe - which is exactly the drift that put a fork's URLs into the
public package. Assert every duplicated field against
.codex-plugin/plugin.json, derive the hand-maintained character counts
instead of trusting them, and require every public URL to sit under the
canonical author.url so publication cannot move off this repository
without turning the check red.
Also: guard the canonical-copy comparison against a missing plugin copy
(it raised FileNotFoundError instead of reporting), scope the hygiene
scan to the packaged surface instead of walking .git, and restore the
CLAUDE.md path-filter rationale the port deleted from the workflow.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): bundle every resource the canonical skill references
OpenAI's submission contract says each skill must include any referenced
scripts, templates, or assets, and the Codex skill layout has no shared-
resource mechanism, so skills/avoid-ai-writing/SKILL.md (byte-identical to
root SKILL.md) now ships with synced copies of detector/patterns.js,
detector/validate.js, detector/CATEGORIES.md, scripts/check-style.js, and
examples/ at the same relative paths. scripts/sync-plugin-skill.sh produces
them and the existing regenerate-then-diff CI gate covers them. A new smoke
test runs check-style and the preservation validator from inside the
bundled tree and from an extracted package.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): manifest supportURL, ancestry-checked baseCommit, policy.products
interface.supportURL now lives in .codex-plugin/plugin.json and the listing
value is validated against it. Both submission files record baseCommit as
the origin/main merge-base and the validator checks it is an ancestor of
HEAD so it cannot drift silently; the verifier's copied patterns.js joins
the deterministic-resource inventory. The validator accepts
policy.products with CHAT and/or CODEX per the current agents/openai.yaml
schema and keeps rejecting unknown policy keys, with tests.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): follow main to 3.29.0 after #128 landed
Bump .codex-plugin/plugin.json and the submission metadata to 3.29.0, set
baseCommit to the new origin/main merge-base, and regenerate the bundled
copies so the sync gate is clean on the merge ref.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): changelog and README for the plugin package; harden packager and validator
Qodo re-review items: a dated 3.29.0 changelog entry and a README section
for the native ChatGPT/Codex package; the packager and validator now reject
symlinked top-level package files; JSON loading rejects a non-object root
with a validation error instead of crashing, with tests for list and null
roots and for the symlink case (skipped where symlinks need privileges).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): packager and validator hardening, lone-CR preservation, workflow paths
Qodo re-review items 6-11: the marketplace policy no longer demands
install-time authentication for a skills-only package (ON_USE, the only
other documented value); the packager rejects an output path that is a
packaged input or sits inside an included directory and fails on a missing
top-level package file instead of silently omitting it; the validator
type-checks nested submission objects before access; the preservation
validator normalizes CRLF only, so a lone carriage return changed inside
code is reported again; LICENSE joins the workflow path filters. Tests for
each; bundled validator copies re-synced.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): marketplace authentication policy is first-use, not install-time
The skills-only package has no authentication flow or hosted service. The
marketplace docs say policy.authentication decides whether auth happens on
install or first use; first use never triggers for local skills, so ON_USE
replaces ON_INSTALL. (Qodo item 6, deferred from the previous commit because
the implementer sandbox could not write .agents/.)
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): graph validator rejects malformed JSON cleanly; canonical URL is a constant
Qodo items 8 and 9. validate_connections.py now checks the graph root and
edge field types and reports through its validation path instead of
raising, with a test script wired into CI. validate-openai-plugin.py pins
CANONICAL_PROJECT_URL and requires author.url to equal it, so changing every
public URL to a fork no longer passes; test added.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(port): bound SVG parsing and stop empty skill names polluting the graph set
Qodo items 19 and 20. The validator rejects SVGs carrying <!DOCTYPE or
<!ENTITY declarations and anything over 256 KiB before handing text to
ElementTree, closing the entity-expansion path; a skill whose frontmatter
lacks a name reports that error once instead of inserting an empty name
that cascades into router-graph errors. Tests for both.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* ci(port): full-history checkout so the baseCommit ancestry check can run
The validator's merge-base --is-ancestor check needs the base commit in the
checkout; actions/checkout's default depth of 1 made CI report it as "not a
valid commit name".
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Conor Bronsdon <120674402+conorbronsdon@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
The finditer fix shipped in #114 without a test that can fail — a
reversion to first-match-only scanning would stay green and quietly
undercount. One assertion closes it: a two-ref line must report 2 hits.
Verified: intact script passes; mutating scan_line to first-match-only
fails with "expected 2 hits on a two-ref line, got ['scripts/check-style.js']".
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Delivers the outstanding findings from the #110 reviews, which were posted
before merge but not addressed in it:
- FILENAME can accept path segments, so plugins/avoid-ai-writing/SKILL.md
and corpus/human/essay-01.md now block — every real file under plugins/
is nested, so that REPO_DIRS entry could previously never fire (the hole)
- right boundary: patterns.json no longer blocks via its patterns.js prefix
- left guard includes _, so my_scripts/foo.js is prose
- a markdown link with an http(s) target drops text and target together —
the error message recommends exactly that form, so the gate no longer
blocks its own advice
- finditer per line: the count and the quoted matches are now honest when
one line carries two refs
- the review's precision matrix is committed as an always-on self-test
(assert on every run; CI executes this script for the drift check, so it
rides along with no workflow change). examples/.json documented as a
deliberate pass per the review's ruling.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* check-pattern-count: assert CLAUDE.md's copy of the category count on every push
CLAUDE.md's don't-restate-it sentence quotes the README bullet, and its copy
is tracked only by .ssot.yaml, which runs on release and weekly cron - so a
same-repo edit could sit stale for up to a week (how #95's 46-vs-61 lived
unnoticed). The sed pattern mirrors .ssot.yaml's regex for the copy, so the
two guards cannot read different sentences.
Controls: clean tree passes; 61->62 mutation fails with the drift message;
a reworded sentence fails with its own message pointing at both guards.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EKwz2XfwaMD6uR5ABmVaKq
* count guard: actually trigger on CLAUDE.md edits, survive a missing file, take the first match
All three findings from the adversarial review of #111:
- HIGH: plugin-skill-sync.yml's paths filter omitted CLAUDE.md, so the
guard never ran on the edits it exists to catch (PR #106: zero check
runs). Added to both triggers.
- MEDIUM: under set -euo pipefail a missing CLAUDE.md killed the script
with sed's raw error and exit 2 before the friendly branch. Explicit -f
check with its own message and exit 1.
- LOW: greedy sed took the LAST match on a line where a first-match regex
engine takes the first; extraction is now grep -o | head -n1 (file-order
first match) and the mirror-claim comment states the semantics honestly.
Controls, exit codes checked unpiped: clean 0; mutation 1; reworded 1;
missing file 1; same-line double-mention resolves to the first match.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EKwz2XfwaMD6uR5ABmVaKq
---------
Co-authored-by: Claude <noreply@anthropic.com>
The anchored rewrites catch EDITS to a span they already know about. A brand
new SKILL.md section that names a repo path passes them untouched and lands
in a rule users curl into a project where none of this repo's files exist.
That is how the --style section nearly shipped pointing at
scripts/check-style.js and examples/, caught by hand in #99 rather than by
the guard.
The gate scans the generated body and exits 1, naming the match and the line
number it would occupy in the rule. Two structural choices:
Only `body` is scanned. The attribution header names
scripts/sync-cursor-rules.sh and lives in cursor_fm, so it is exempt by
construction rather than by a line-range carve-out that would drift when the
header changes.
It runs before the write, so a failing generation leaves no bad artifact on
disk to be committed by accident.
Precision is the whole difficulty, since the bare directory names collide
with ordinary prose in this document. A match therefore has to name a FILE
(`scripts/check-style.js`, `examples/<name>.json`), which is what every real
reference here looks like. An earlier revision matched bare directories and
false-positived on unmodified SKILL.md: `docs/technical-blog` is a context
pair, not a path. Three further exemptions, each a precision call: a left
word boundary, so `manuscripts/x.md` stays prose; anything inside an http(s)
URL, which is the portable form and also what this gate's own message tells
an author to switch to; and README/CHANGELOG/CONTRIBUTING/CLAUDE, which
every project has and which this skill's prose already names.
Verified with a 15-case matrix. Must-pass: manuscripts/, transcripts/,
superscripts/, examples/counterexamples, docs/technical-blog, README.md,
and two GitHub URLs whose paths contain detector/ and examples/. Must-block:
the #99 near-miss shape, `examples/<name>.json`, `detector/CATEGORIES.md`,
./scripts/self-scan.js, and the bare filenames validate.js and PROOF.md.
Removing the probe line returns exit 0 and leaves the rule unchanged.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat: optional --style house-style layer (config-driven, points at Vale)
Implements the config-driven design recorded in #88, which #76 and the fork
review converged on. No bundled guides: the layer applies register/voice
directives and removes AI tells on top of whatever mechanics you enforce.
--style ./house.json applies a user-supplied JSON config (register +
mechanics) and scripts/check-style.js verifies the CHECKABLE mechanics
deterministically: quotes and latinAbbrev gate the exit code (0 clean /
1 hard / 2 tool error), headings, emDash and spellNumbersUpTo are advisory,
serialComma is never checked. The docs scope the verb accordingly rather
than claiming "mechanics are verified" flatly. examples/ ships two generic,
guide-neutral starters plus the schema, and links #88 for the licensing
rule.
A bare --style "APA" is a best-effort fallback, not a feature: SKILL.md
instructs the model to print a no-compliance-claim status line and not to
reproduce the guide's text. Those are instructions rather than checked
rules, and the docs say so instead of asserting the behaviour as fact.
--style is listed in the SKILL.md invocation line and has an explicit
composition rule with --voice/--context, since the file specifies
composition for every other axis.
README: the "House style is a different job" section said "There's no
--style input", which this makes false. The first paragraph now describes
the config input and reconciles with the heading (enforcing a PUBLISHED
guide is the different job). The Vale paragraph and the heading anchor are
unchanged.
cursor-rules: the ported rule would have told a Cursor user to run
scripts/check-style.js and read examples/, neither of which ships in the
.mdc. Two anchored spans in sync-cursor-rules.sh rewrite those the way
span 3 already handles detector/validate.js, so the port stays
self-contained. Worth noting the drift guard only covers edits to anchored
spans, not newly added SKILL.md sections that introduce repo references.
The checker went through three adversarial review rounds, and each round
found the previous round's fix had introduced a new way to hard-fail a
correct document or to miss a real one. The tests pin all of them: markdown
link titles, reference definitions (including escaped quotes in a title),
HTML attribute values, nested and tilde fences, BOM'd frontmatter, URLs
containing parentheses, parentheticals that wrap or span a code block, and
a stray "(" that must not suppress later findings, and prose containing a
comparison ("n<N ... >") that must not be mistaken for an HTML tag. Masking runs refdef ->
links -> tags, in that order, because masking a link destination first
makes an ordinary "[a](url): text" line look like a reference definition.
Link masking walks to the matching paren and scans linearly; the regex form
was quadratic (22.7s on a hostile line, now 4ms). resolveConfig decides
path-vs-name by shape so a cwd file can't shadow a bundled example, the CLI
parses by position, a config with "mechanics": null or [] exits 2 rather
than a false-green 0, and advisory findings print instead of hiding behind
--json.
Version 3.22.3 -> 3.23.0 in SKILL.md frontmatter, package.json and
plugin.json; CHANGELOG entry under a dated heading; plugin and cursor
copies regenerated.
No detector changes: catalog counts unchanged (61 / 112). 32 tests in
scripts/check-style.test.js under npm test; detector-test.yml path filters
extended to scripts/** and examples/**.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style: mask indented code, tighten frontmatter open, announce the resolved mode
Review fixes applied on top of the submitted branch:
- Indented code blocks (4+ spaces / tab after a blank line, outside a list)
are masked, so pasted terminal output can't hard-fail a correct document.
Lazy continuation and list-item content stay checked; a code block nested
in a list item needs a fence. Was the largest undocumented false positive.
- A document opening with a thematic break is no longer read as frontmatter
(which silently swallowed everything to the next ---).
- The bare-name traversal regex was dead code its test never reached; a bare
name is a single path segment by construction, so the guard is now a
comment stating that argument, and a test pins dot-bearing names.
- Config runs open by naming the resolved config, mirroring the fallback's
status line, so which of the two modes ran is always explicit in output.
- Known-limitations lists gain the double-backtick span and next-line
reference-definition title gaps; examples/README.md joins the self-scan
budgets; CHANGELOG updated; cursor-rule anchors follow the SKILL.md edit.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Conor Bronsdon <120674402+conorbronsdon@users.noreply.github.com>
The Cursor port was a hand-made copy stranded at v3.16.0 while
SKILL.md reached v3.22.3 — its own README said 'no automated sync
today, open an issue if drift becomes a problem.' It did.
scripts/sync-cursor-rules.sh now generates the .mdc from SKILL.md:
Cursor frontmatter with the version derived from the SKILL.md
frontmatter, plus the three portability rewrites a copied-out rule
needs (no repo self-reference, no CATEGORIES.md citation, manual
preservation check instead of node detector/validate.js). Each
rewrite is anchored on exact upstream text and exits non-zero if the
anchor stops matching once, so an upstream edit to a ported span
breaks CI here instead of silently shipping a wrong rule.
plugin-skill-sync workflow regenerates the rule on every SKILL.md
change and fails on drift; cursor-rules/** added to its path filters
so a hand-edit to the .mdc alone can't dodge the check.
Negative control run: mutating a ported span in SKILL.md makes the
script exit 1 with an actionable message; restoring it regenerates
byte-identically (second run idempotent).
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Catch promo-surface drift from the release that causes it
The pattern count and word-table count are already policed inside this repo:
check-pattern-count.sh derives both from SKILL.md and fails CI if the README
disagrees. Nothing policed the second link — four surfaces in other repos
quote those numbers, and a release moves the number here while they sit still.
That drift cannot be caught from the other side. Their files do not change on
release day, so no pre-commit hook over there ever has a commit to fire on.
It went unnoticed for three weeks: three of the four surfaces were still on
53 pattern categories and 109 table entries.
So the check runs here, on release, with a weekly backstop:
- .ssot.yaml declares the README bullets as canonical and the four surfaces
as copies (dogfoods conorbronsdon/ssot-check)
- promo-drift.yml clones the surfaces as siblings and runs the check
- promo-drift-report.py turns the JSON into a readable issue body
A surface that cannot be read is reported as NOT CHECKED and does not fail
the job — conorbronsdon-site is private, and failing red every week over a
missing token trains people to ignore the check. It is always printed. Set
SITE_REPO_TOKEN to bring it into coverage; no code change needed.
Verified against real clones of all four surfaces: in-sync exits 0, a stale
number exits 1 with file:line, an unreadable surface exits 0 and says so, and
a reworded canonical bullet is a hard failure rather than a silent pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YA7143ow5qvWZghbeQKiUd
* Drop the site from the manifest; the check now needs no credential
conorbronsdon.com/builds floors both counts instead of quoting them, so there
is nothing left to keep in sync there. That removes the only private surface,
which removes the only reason this workflow wanted a PAT.
Every tracked surface is now a public repo and the job runs on its own
GITHUB_TOKEN. The not-checked path stays — a surface repo can still be
renamed or fail to clone, and that must read as a coverage gap, not a pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YA7143ow5qvWZghbeQKiUd
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Adds a preservation validator, a self-scan with PROOF.md, over-correction guardrails, a false-positive intake, and a two-class control corpus with the project's first FPR, TPR, and AUC.
Splits Tier 1 into 1A frequency markers and 1B clarity edits, and fixes two detector defects the measurement found (#67, #69).
Findings and open decisions: #70, #71, #72, #73.
The README advertised a "109-entry word replacement table". The real count is 111 (59 Tier 1 + 40 Tier 2 + 12 Tier 3). Stale since 176b5a0 because nothing checked it.
Extends check-pattern-count.sh to derive the word count from the Tier 1/2/3 tables and assert it against the README bullet. Already wired into CI via plugin-skill-sync.yml.
Headers are detected positionally (the row before the |---|---| separator) rather than by label: Tier 1/2 use "| Replace | With |" while Tier 3 uses "| Word | What to do |", so label-matching silently counted two headers as data — which is how the first pass of this PR arrived at 112. Separator matching tolerates alignment colons. A per-tier non-zero assertion fails with a distinct "fix the counter, not the README" message when a heading stops matching, so a broken counter cannot enshrine a wrong number.
Comprehensive doc review after the 3.4->3.7.2 churn. The pattern count
had rotted across files (README said 42, CLAUDE.md said 36, reality is
46 detection categories in SKILL.md).
- Fix the count to 46 and keep it in ONE user-facing place (the README
"46 pattern categories" bullet). README heading reframed to "Pattern
reference" (representative examples, not an exhaustive census), and the
table extended with the 7 missing categories (placeholders, citation
markup, UTM, gap-filling, hyphenated-pair, infomercial, low-TTR).
- De-duplicate the count: CLAUDE.md and detector/CATEGORIES.md now
reference SKILL.md + CI instead of restating their own numbers.
- Add scripts/check-pattern-count.sh + wire into the CI workflow: it
derives the count from SKILL.md's detection ### entries (excluding the
3 writer-side tests) and fails if the README number drifts. Drift is
now a red check, not silent rot.
- Fix stale detector/patterns.js version comment and the marketplace.json
description (was "detection-only mode").
No SKILL.md / version change — docs + CI only.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: distribute as a Claude Code / Cowork plugin
Package the skill as a single-plugin marketplace so it can be installed
via /plugin instead of a bare clone. This is the only path that works in
Claude Cowork, which loads skills exclusively from installed plugins
(see #12).
Root SKILL.md stays the single source of truth; the plugin's bundled
copy at plugins/avoid-ai-writing/skills/avoid-ai-writing/SKILL.md is
generated by scripts/sync-plugin-skill.sh. A CI workflow regenerates it
and fails on drift or a plugin.json/SKILL.md version mismatch.
Validated with `claude plugin validate` and a full local
add-marketplace / install / inspect / uninstall cycle.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: parse plugin version safely in sync script
* fix: harden plugin version parsing in sync script
* harden skill-version parsing + plugin install docs
Builds on Copilot's plugin.json JSON-parser fix:
- sync-plugin-skill.sh: read the version only from the SKILL.md
frontmatter block (not anywhere in the file), strip CR, and fail with
a clear message if it's unparseable — closes the loose/false-green
side of the version check that the JSON parser already closed for
plugin.json.
- .gitattributes: pin *.md to LF so a CRLF checkout can't forge a
version mismatch or mask skill drift.
- README: add /reload-plugins to the install steps (skills don't
activate until reload/restart) and note updates are version-gated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Francisco Quinteros