Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- GENERATED by claude-power-pack - scripts/codex-skill-sync.py; edit .claude/commands/security/scan.md instead -->
# Security Scan
Run a full security scan using native checks plus any available external tools.
> **Semantic code review?** For code-logic vulnerabilities - SQL injection, XSS,
> broken authorization, insecure credential handling - use Claude Code's native
> **`/security-review`** (and its GitHub Action). This command is the
> *deterministic* complement: secret scanning (gitleaks + patterns) and
> dependency CVE audits (`pip-audit`, `npm audit`). Run both for full coverage.
## Arguments
- `--json` - Output as JSON (machine-readable)
- `--verbose` - Show matched patterns and additional details
- `--path <dir>` - Scan a specific directory (default: current project)
## What's Checked
### Native (always available)
- `.gitignore` coverage for sensitive file patterns
- File permissions on secrets/keys
- High-confidence secret patterns (AWS keys, GitHub tokens, API keys)
- `.env` files tracked by git
- Debug flags in production configs
### External (auto-detected)
- **gitleaks** - secret detection in working tree
- **pip-audit** - Python dependency CVEs
…
The line at the top of this page pins the label git:20260911.3a0a7c8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1682 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
cooneycw/claude-power-pack · 21 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dxjnsmn4z3juukos
GET https://markdownregistry.com/api/v1/resolve?ref=cooneycw/claude-power-pack/security-scan
GET https://markdownregistry.com/api/v1/blob/70f836e06beaef6aa4b8e8113e0afdae8d942eea4efe9db069ea32c2d27ce30e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
cooneycw/claude-power-pack · .claude/skills/best-practices/SKILL.md · Routes to topic-specific best practices skills instead of loading them all. Use for Claude Code help, tips, or a how to…
cooneycw/claude-power-pack · .claude/skills/boot/SKILL.md · Menu-driven session identity registration for Kyle-compatible local-network discovery. Use to boot or register a…
cooneycw/claude-power-pack · .claude/skills/browser-tiered/SKILL.md · Use the bdg CLI for lightweight work and escalate to Playwright MCP for complex flows. Use for browser automation…
cooneycw/claude-power-pack · .claude/skills/cicd-verification/SKILL.md · Build system, health check, pipeline and container patterns. Use for CI/CD - a pipeline, Makefile generation, GitHub…
cooneycw/claude-power-pack · .claude/skills/claude-md-config/SKILL.md · CLAUDE.md structure, optimization and conventions. Use when writing or reviewing a CLAUDE.md, during project setup, or…
cooneycw/claude-power-pack · .claude/skills/code-quality/SKILL.md · Code review, testing and quality patterns. Use when reviewing code, deciding what testing a change needs, or judging…
cooneycw/claude-power-pack · .claude/skills/context-efficiency/SKILL.md · Progressive disclosure, token budgets and optimization. Use when context is filling up, when tokens must be cut to a…
cooneycw/claude-power-pack · .claude/skills/documentation/SKILL.md · Generate C4 architecture diagrams as GitHub-renderable Mermaid, and PowerPoint slides. Use to update docs, or draw a c4…
cooneycw/claude-power-pack · .claude/skills/evaluate/SKILL.md · Domain-aware prompts for multi-model analysis. Use to evaluate an architecture, concept, algorithm, ui-design or…
cooneycw/claude-power-pack · .claude/skills/hooks-automation/SKILL.md · Hook types, lifecycle and automation patterns. Use when adding or debugging hooks such as SessionStart or…
cooneycw/claude-power-pack · .claude/skills/idd-workflow/SKILL.md · IDD workflow with git worktrees and issue hierarchy. Use for issue driven development, creating a git worktree, or…
cooneycw/claude-power-pack · .claude/skills/infrastructure-hardening/SKILL.md · Validation gates, runtime contracts, canary validation and sentinel files. Use after a repeated failure, or for…
cowork-os/cowork-os · resources/plugin-packs/codex-security/skills/security-scan/SKILL.md · Use when the user asks for a repository-wide or scoped-path security scan.
fusengine/agents · plugins/security-expert/skills/security-scan/SKILL.md · Use when scanning for XSS, SQL injection, command injection, hardcoded secrets, or any OWASP Top 10 vulnerability…
ray0907/security-scan · SKILL.md · Use when a user asks to scan a repository for dependency vulnerabilities, license compliance, insecure code patterns…