mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-11-15 09:11:54 +00:00
The skill security audit's detect step only looked for SKILL.md one or two
folders deep, so plugin-layout skills and engineering/skills mirrors were
skipped, and its path filter missed eleven newer domains. Detection now
walks up to the nearest SKILL.md, the path filter is gone, and the audit
re-runs on ready_for_review.
Before turning it on, all 409 skills pass `--strict`:
- Fixed: full-page-screenshot pasted the output path into shell commands
and a generated Python script (execFileSync + JSON-quoted paths now);
senior-fullstack scaffolds fell back to hardcoded secrets when the env
var was unset (now required), and the scaffolder crashed on every
template (str / str).
- Cleaned: senior-security's __import__('datetime'), epic-design's
"You are now" opener.
- False positives marked with `noqa: SEC-AUDITOR (reason)`; the auditor
gains an auditor:ignore-start/end block for template-string text.
Bumps every changed plugin one patch above dev (G11).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLjaj5gnwaZdF3RyDn
|
||
|---|---|---|
| .. | ||
| .claude-plugin | ||
| agents | ||
| commands | ||
| skills/coding-agent-rollout | ||
| README.md | ||
coding-agent-rollout
One engineer's Claude Code setup is a preference. A team's is a policy.
Settings merge from five scopes, permissions.allow arrays combine across
files, and deny beats ask beats allow wherever it is written. Nobody can read
the effective policy from one file, so nobody notices when a permissive user
file undoes a careful shared one, or when an unpinned MCP server changes
overnight. This plugin makes the policy readable and then checks it.
Install
/plugin marketplace add alirezarezvani/claude-skills
/plugin install coding-agent-rollout
Use
/cs-claude-rollout . # full audit of this repo
/cs-claude-settings-lint . /etc/claude-code/managed-settings.json
Or run the scripts directly. Each has --help, --sample and --output json:
| Script | Phase | What it checks | Exit codes |
|---|---|---|---|
settings_linter.py |
Guardrails | Blanket and destructive allows, dead rules, secrets in env, committed local settings, MCP auto-approval, network hooks, managed bypass switch |
0 · 2 · 3 · 4 |
mcp_plugin_inventory.py |
Inventory | Every MCP server, plugin and marketplace; allowlist, pinning, plain-http remotes, committed secrets | 0 · 2 · 3 · 4 |
claude_md_layering_audit.py |
Instructions | Resident vs on-demand layers, @imports (4-hop limit), duplicates, contradictions, secrets, size | 0 · 2 · 3 · 4 |
adoption_tracker.py |
Adoption | Counts-only member summaries from local transcripts; team stage PILOT / SPREADING / EMBEDDED / STALLED | 0 · 2 stalled · 3 |
Design decisions
- Verified, not remembered. Every settings key, scope, path and limit was checked against the official Claude Code docs. Settings ship fast, so unknown keys are INFO, not errors.
- Read-only. No script edits a settings file. They report; you decide.
- Privacy first for adoption. The tracker never emits prompt text, file content, or tool inputs other than a skill name. Teams share the JSON summary, never transcripts.
- Baseline policy included.
assets/managed-settings.example.jsonlints clean and is a sane day-one policy.
Distinct from
claude-coach— coaches one person.skill-retro— improves installed skills from session evidence.security-guidance— a hook that warns on risky code as it is written.
License
MIT