Bitdefender (and similar heuristic AV/EDR products) quarantine the
hunt-playbooks reference because it lists the command-line patterns
associated with LOLBin abuse (certutil -decode, regsvr32 /s /u /i:http
scrobj.dll, mshta URL, etc.). The strings appear inside markdown
tables and cannot execute from a .md file — this is defensive
threat-hunting documentation.
Added a banner at the top that:
- States the defensive-doc intent explicitly
- Lists the binaries cited and why they appear
- Tells affected users how to allow-list the path
- Links to the tracking issue
Closes#533
The /si:extract command and its skill-extractor agent had no guard
against the Claude Code skill-spec reserved name fragments. Users
reported the agent autogenerating skills like 'claude-code-settings',
'claude-mcp-tools', etc. — all of which violate the spec.
- Add explicit reserved-fragment rule to both the slash-command
SKILL.md and the agent definition.
- Recommend the 'cc-' prefix for Claude Code-specific skills
(cc-settings, cc-maintenance, cc-mcp-tools).
- Add the check to both quality-gate checklists so the agent
surfaces a rename before writing files.
Closes#537
Five SKILL.md files linked to references/*.md files that don't exist
on disk:
- onboarding-cro, paywall-upgrade-cro, page-cro → references/experiments.md
- programmatic-seo → references/playbooks.md
- seo-audit → references/ai-writing-detection.md, references/aeo-geo-patterns.md
The 4 CRO/pSEO links pointed to placeholder content that was never
authored — removed the link lines (the surrounding sections still
hold the substantive guidance). The seo-audit References section is
re-anchored to the 4 reference files that actually exist
(seo-audit-reference, cwv-thresholds, eeat-framework, schema-types).
Closes#586
The lowercase pull_request_template.md was an exact duplicate of
PULL_REQUEST_TEMPLATE.md. On case-insensitive filesystems (Windows,
default macOS), git clone emits a path-collision warning and only
one file lands in the working tree.
Closes#545
Promotes the 11 commits accumulated on dev since v2.4.4 into a tagged
release before opening the dev->main PR.
Version bumps (root-level only — per-skill version stamps unchanged):
.claude-plugin/marketplace.json metadata.version: 2.4.4 -> 2.4.5
CLAUDE.md 'Version:' headers (x2): v2.4.4 -> v2.4.5
CLAUDE.md 'Last Updated': May 10 -> May 11, 2026
Deliberately NOT bumped:
- slo-architect plugin version (marketplace.json line 643) stays 2.4.4
-- that's the skill's own release stamp, not the repo version
- SKILL.md frontmatter versions in engineering/skills/slo-architect/
and engineering/slo-architect/skills/slo-architect/ -- same reason
CHANGELOG.md changes:
- [Unreleased] block renamed to [2.4.5] - 2026-05-11
- Title broadened to include 'Count-Truth Reconciliation' alongside the
original 'Skill Expansion Phase 1+2+3+4 (+ ship-gate)'
- 'Changed' totals corrected to file-system truth:
Skills: 235 -> 246 (was claimed 235 -> 238)
Tools: 314 -> 359 (was claimed 314 -> 325)
References:435 -> 485 (was claimed 435 -> 447)
Agents: added (28 -> 27, was missing)
Commands: 27 -> 33 (was claimed 27 -> 30)
Plugins: added (30 -> 33, was missing)
- 'Fixed' subsection: added bullets for #608 (count corrections) and
#609 (marketplace registry + integrations.md), plus
skill-security-auditor self-skip fix
Why the v2.4.4 unreleased totals were wrong: the entry was drafted
mid-cycle and never reconciled before tagging. #608/#609 caught the
drift. The v2.4.5 totals now reproduce from one find/python3 command
each (commands documented inline in the changelog bullets).
PR #607 shipped '188 skills, 30 agents, 3 personas, 30 marketplace plugins'
based on a stale codex-sync output that I trusted without verifying. The
actual file-system counts are:
Skills: 246 (250 SKILL.md files; 4 deduped because chaos-engineering,
feature-flags-architect, kubernetes-operator and
slo-architect each ship as both an umbrella entry and
a standalone plugin)
Tools: 359 .py files under */scripts/* (unchanged, was correct)
Refs: 485 .md files under */references/* (unchanged, was correct)
Agents: 27 (20 canonical cs-*-prefixed + 7 personas; excludes
agents/CLAUDE.md, personas/README.md, personas/TEMPLATE.md)
Commands: 33 .md files under commands/ (unchanged, was correct)
Plugins: 33 in .claude-plugin/marketplace.json (was '30' in the
Status line and README badge area)
Every number now reproduces from a single deterministic command:
find . -name SKILL.md -not -path './.gemini/*' -not -path './.codex/*' \
-not -path './site/*' -not -path './docs/*' \
-not -path './.git/*' | wc -l # -> 250 raw
find agents -name 'cs-*.md' | wc -l # -> 20 cs-* agents
ls agents/personas/*.md | grep -v -E 'README|TEMPLATE' | wc -l # -> 7
python3 -c "import json; print(len(json.load(open('.claude-plugin/marketplace.json'))['plugins']))" # -> 33
Surgical edits only: changed the number, left every other word in place.
Files touched: CLAUDE.md (7 lines), README.md (5 lines), docs/index.md
(4 lines), docs/getting-started.md (2 lines), mkdocs.yml (1 line).
Security scanners legitimately reference dangerous patterns (eval, os.system,
subprocess shell=True, etc.) inside their own regex pattern definitions and
human-readable risk/fix descriptions. Auditing the auditor itself produced
17 CRITICAL false positives — all from its own pattern table. ship-gate had
the same issue (2 CRITICALs on a check description and a variable name
called eval_findings).
Fix:
- Add 'noqa: SEC-AUDITOR' / 'auditor:ignore-line' line-suppression directive
to all three scan loops (code patterns, prompt-injection markdown,
pip/npm runtime install detection).
- Annotate the 179 pattern-definition lines in skill_security_auditor.py
(regex, risk, fix entries) and 4 cleanup shutil.rmtree calls.
- Annotate ship-gate's two flagged lines (SEC-13 check description and
eval_findings variable usage).
- Annotate SKILL.md and references/threat-model.md tables that document
attack patterns for human readers (HTML comment <!-- noqa: SEC-AUDITOR -->).
Verified end-to-end:
skill-security-auditor self-audit: 17 CRITICAL -> 0 (PASS)
ship-gate self-audit: 2 CRITICAL -> 0 (PASS)
slo-architect: PASS (0/0)
project-management WARN unchanged (no top-level SKILL.md, expected)
Auto-regenerated by scripts/generate-docs.py after the post-restructure
fix. Covers slo-architect, ship-gate, chaos-engineering, kubernetes-operator,
feature-flags-architect, llm-wiki, tc-tracker, and 185 other skills now
properly surfaced under their domain index pages.
After PR #593 restructured umbrella plugins, every sub-skill landed at
<domain>/skills/<name>/SKILL.md. The doc generator's is_sub_skill heuristic
treated len(parts) > 2 as nested, so all 188 skills got flagged as 'children
of "skills"' (a non-existent parent) and were never written to docs/.
Recognise <domain>/skills/<name>/ as the canonical top-level layout.
Backwards-compatible with playwright-pro/skills/<sub>/ standalone-plugin
sub-skills (those legitimately have a real parent at parts[1]).
Result: 0 -> 192 skill pages emitted.
PR #527 (@rx4u) submitted a pre-production audit skill that was based on the
pre-#593 layout (skills directly under engineering/). After #593 landed, the
diff would have undone the entire restructure (4500+ rename ops). Re-applying
the actual new content at the correct post-restructure path.
What landed:
- engineering/skills/ship-gate/SKILL.md
- engineering/skills/ship-gate/references/checks.md
- engineering/skills/ship-gate/references/patterns.md
- engineering/skills/ship-gate/scripts/ship_gate_scanner.py
Verified:
- python3 ship_gate_scanner.py --help → OK
- python3 ship_gate_scanner.py --version → ship-gate 1.0.0
- 1671 tests pass (was 1666; +5 for ship-gate smoke + integrity)
- engineering/.claude-plugin/plugin.json: 48 → 49 skills, v2.4.2 → v2.4.3
- marketplace.json: engineering-advanced-skills entry updated to match
Closes#527.
Co-authored-by: Rajaraman Arumugam <rx4u@users.noreply.github.com>
https://claude.ai/code/session_01Dq12xJakFRxwaoU8Pqejdm
chore: resolve 4 open PRs (#596, #597, #582, #517) on clean dev base
Consolidates four ready-to-merge PRs that had become dirty against the
post-restructure dev branch. Conflict in tests/test_skill_integrity.py
resolved by keeping the broader script_globs version (includes .ps1).
Closes#517, #582, #596, #597.
test_scripts_dirs_have_python_files was asserting every scripts/ dir
contains at least one .py file. The full-page-screenshot skill ships
a .mjs (Node ESM) script and triggered a false-positive failure.
Broadens the check to accept any of .py, .mjs, .js, .ts, .sh while
keeping the same intent: scripts/ dirs must not be empty.
Verified: full pytest suite goes from 1 failed / 1611 passed to
725 passed in tests/test_skill_integrity.py alone.
https://claude.ai/code/session_01Dq12xJakFRxwaoU8Pqejdm
Phase 0 of the multi-skill build: ship the two stdlib-only tools that
the rest of the work depends on.
- scripts/sync_skill_bundles.py: mirror a standalone plugin's
SKILL.md + scripts/ + references/ + assets/ into its domain-bundled
location. --check exits 1 on drift; --sync rewrites the mirror.
- scripts/check_plugin_json.py: validate plugin.json against the
strict ClawHub schema (exactly the 8 allowed fields, semver version,
author{name,url}, skills as string or array — bare "./" rejected per
Claude Code v2.1.107+).
Verified: --all run reports OK on all 30 existing plugin.json files;
sync --check correctly detects missing mirrors. Karpathy-coder gate:
both files score 85/100 under strict (single nesting-depth WARN, no
FAIL) — better than the canonical karpathy-coder tools themselves.
https://claude.ai/code/session_01Dq12xJakFRxwaoU8Pqejdm
`engineering/skills/full-page-screenshot/scripts/full-page-screenshot.mjs` is
a legitimate 35KB JavaScript module, but the test only matched `*.py` and
asserted the dir was empty. This caused `test_skill_integrity` to fail on
dev's HEAD (pre-existing breakage, surfaced when CI ran on PR #601).
Broadens the check to accept any common script extension:
.py, .mjs, .js, .ts, .sh, .ps1. The test's intent — "scripts/ shouldn't be
empty" — is preserved; the implementation no longer over-restricts language.
Adds toprank (https://github.com/nowork-studio/toprank) — open-source MIT
plugin with 9 SEO and Google Ads skills (107 GitHub stars).
Co-authored-by: ununununium <43973612+ununununium@users.noreply.github.com>
Closes-PR: #517
- Adds project-management/.mcp.json registering Atlassian's official Remote
MCP server (https://mcp.atlassian.com/v1/sse) as a plugin-bundled SSE MCP.
- Updates project-management/README.md Setup section to reflect bundled-MCP
reality (OAuth handled automatically; no API tokens in the repo).
- Closes the doc/code drift between CLAUDE.md's "Atlassian MCP integration"
claim and the previously absent .mcp.json file.
Co-authored-by: FreyaFujo <172978998+FreyaFujo@users.noreply.github.com>
Closes-PR: #597
`.mcp.json` is the canonical filename Claude Code expects for plugin-bundled
MCP server configuration. The auditor's hidden-file rule was flagging it as
HIGH severity, blocking the `--strict` quality gate documented in CLAUDE.md.
Co-authored-by: FreyaFujo <172978998+FreyaFujo@users.noreply.github.com>
Closes-PR: #596
Karpathy-style review of commit 3806b9b (the prior PR commit) caught real
issues that I missed: agents weren't fully equipped per the optional but
recommended fields in the official sub-agents spec.
Changes:
- engineering/agenthub/agents/hub-coordinator.md: narrow Bash(node *) (too
broad per defense-in-depth) -> moved node into disallowedTools; add
maxTurns: 100 (orchestrators run long); add skills: agenthub:agenthub
(preload the plugin's own guidance into agent context)
- engineering-team/self-improving-agent/agents/memory-analyst.md:
add maxTurns: 30 to bound runaway analysis loops
- engineering-team/self-improving-agent/agents/skill-extractor.md:
add disallowedTools (rm/curl/wget) — agent has Write+Edit so defense-in-
depth applies; add maxTurns: 30
- engineering/karpathy-coder/agents/karpathy-reviewer.md: fix skills field
format from path-style "engineering/karpathy-coder" to spec-correct
namespaced name "karpathy-coder:karpathy-coder" (the path syntax is the
cs-* orchestrator template convention; the official sub-agents spec uses
skill names per code.claude.com/docs/en/sub-agents); add maxTurns: 30
All 6 plugin agents (4 here + 2 in playwright-pro from prior commit) +
the 1 user agent (tech-ingester) now have name + description + tools +
disallowedTools (where write-capable) + model + maxTurns. The skills:
field is set on agents that benefit from preloaded domain skill content.
Functional smoke tests post-fix:
- memory-analyst: PASS (2 turns, 25s, 24K tokens, found 1 real orphan)
- skill-extractor: PASS (0 tool uses, 34s, 17K tokens, generated correct
plan staying read-only with new disallowedTools in effect)
- karpathy-reviewer: PASS (verified in prior session, 28 tool uses)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per https://code.claude.com/docs/en/sub-agents, agents require YAML
frontmatter with name + description, and the field is `tools:` not
`allowed-tools:` (deprecated). Bare `Bash` allows any command including
curl/wget/rm, which violates defense-in-depth.
Changes:
- engineering/agenthub/agents/hub-coordinator.md: add full frontmatter
(name, description, tools allowlist for git/python/node/Agent,
disallowedTools for rm -rf / curl / wget / git push --force, model)
- engineering-team/self-improving-agent/agents/memory-analyst.md:
add frontmatter, read-only tools (Read, Glob, Grep)
- engineering-team/self-improving-agent/agents/skill-extractor.md:
add frontmatter, write tools (Read, Write, Edit, Glob, Grep)
- engineering-team/playwright-pro/agents/test-architect.md:
rename allowed-tools to tools, add model: inherit
- engineering-team/playwright-pro/agents/migration-planner.md:
same rename
- engineering-team/playwright-pro/agents/test-debugger.md:
rename + narrow bare Bash to npx playwright / node / npm patterns,
add disallowedTools for rm / curl / wget / destructive git
- engineering/karpathy-coder/agents/karpathy-reviewer.md:
narrow bare Bash to git read-ops + python, add disallowedTools
All registered agents now load cleanly under the sub-agents spec rather
than falling through to permissive registration.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR #593 moved every skill from <plugin>/<name>/ to <plugin>/skills/<name>/
to satisfy Claude Code's runtime loader. That broke two CI jobs that
hardcoded the old paths:
1. **9 test files** had `sys.path.insert(0, ".../<domain>/<skill>/scripts")`
pointing at the pre-restructure location. Inserted `"skills"` between
the domain and skill segments so imports resolve again.
2. **scripts/sync-codex-skills.py** scanned `<domain>/<skill>/SKILL.md`
and emitted "No skills found in repository". Updated `find_skills` to
prefer `<domain>/skills/<name>/` and fall back to `<domain>/<name>/`
so it works with both layouts (in case any domain hasn't been
restructured yet).
Verified locally:
- `python3 scripts/sync-codex-skills.py --dry-run` finds 178 skills
- `pytest tests/` collects all modules; 3216 tests pass
- 4 pre-existing failures remain (3 argparse duplicates in an
`integrations/` script, 1 strict "must have .py" check on a JS-only
skill) — out of scope for this fix.
