dep-audit
Skill0 starsChanged 3 months agoMITView on GitHub
Audit project dependencies for security vulnerabilities, outdated packages, and license compliance (check dependencies, security audit, are packages outdated).
9 other projects use a version of this.
Adopted by
Most recently taken up by
- provectus/ccw-advanced-claude-code-labtheir own version, first seen Oct 15, 2026
- TJM-NZ/claude-skillstheir own version, first seen Oct 11, 2026
- sd0xdev/sd0x-dev-flowtheir own version, first seen Oct 8, 2026
- sd0xdev/sd0x-harnesstheir own version, first seen Oct 6, 2026
- koach08/claude-code-skillstheir own version, first seen Sep 12, 2026
- leonardoaraujosantos/my_ai_skillstheir own version, first seen Jul 6, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- cacheforge-ai/cacheforge-skills★ 10same name
- koach08/claude-code-skills★ 4same name
- leonardoaraujosantos/my_ai_skills★ 1same name
- InfiniteRoomLabs/agent-ops★ 0same name
- provectus/ccw-advanced-claude-code-lab★ 0same name
- TJM-NZ/claude-skills★ 0same name
- torifo/skills-dep-audit★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- ai-engineerSkill
- api-clientSkill
- changelog-enforcerSkill
- code-cleanup-guardianSkill
- code-reviewerSkill
- contract-testSkill
- db-migrateSkill
- devops-automatorSkill
- env-configSkill
- error-observabilitySkill
- frontend-designSkill
- git-commit-helperSkill
- github-issues-managerSkill
- git-issue-syncSkill
- git-protocolSkill
- handoffSkill
- incident-responseSkill
- init-projectSkill
- karpathy-guidelinesSkill
- market-researcherSkill
- parallel-agent-git-isolationSkill
- product-strategistSkill
- pr-workflowSkill
- rapid-builderSkill
- release-managerSkill
- resumeSkill
- scrutinizeSkill
- shadcn-uiSkill
- skill-builderSkill
- sprint-plannerSkill
- state-machine-diagramsSkill
- state-managementSkill
- surveySkill
- system-architectSkill
- tech-docsSkill
- unstuckSkill
- ux-design-systemSkill
- ux-researchSkill
- webapp-testingSkill
- web-dev-fundamentalsSkill
- workflow-optimizerSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
If audit scope includes "licenses":
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Dependency Audit
Pre-fetched State
Package Manager Detection
!ls package.json composer.json requirements.txt Pipfile pyproject.toml Cargo.toml go.mod 2>/dev/null || echo "No package manager files found"
Node Security Audit
!npm audit --json 2>/dev/null | jq '{vulnerabilities: .metadata.vulnerabilities, total: .metadata.totalDependencies}' 2>/dev/null || echo "Not a Node project or npm not available"
Node Outdated
!npm outdated --json 2>/dev/null | jq 'to_entries | map({name: .key, current: .value.current, wanted: .value.wanted, latest: .value.latest}) | .[:20]' 2>/dev/null || echo "Not a Node project"
PHP Security Audit
!composer audit --format=json 2>/dev/null || echo "Not a PHP project"
PHP Outdated
!composer outdated --direct --format=json 2>/dev/null || echo "Not a PHP project"
Your Task
Audit scope: $ARGUMENTS (blank = all)
1. Security Vulnerabilities
- Parse audit results from pre-fetched data
- Categorize by severity: critical, high, moderate, low
- For each critical/high vulnerability, provide:
- Package name and affected version
- Vulnerability description
- Fix:
npm audit fixor specific version update command
2. Outdated Dependencies
- Flag packages more than 2 major versions behind
- Flag packages with known EOL dates
- Prioritize updates by: security fixes > major features > minor updates
3. License Compliance
If audit scope includes "licenses":
npx license-checker --summary 2>/dev/null || echo "license-checker not available"- Flag any GPL/AGPL in commercial projects
- Flag any unknown licenses
4. Generate Report
DEPENDENCY HEALTH: [HEALTHY | WARNING | CRITICAL]
Security:
Critical: X vulnerabilities
High: X vulnerabilities
Moderate: X vulnerabilities
Outdated:
Major updates available: X packages
Minor/patch updates: X packages
Action Items:
1. [Most urgent — critical security fixes]
2. [High priority — security + major updates]
3. [Routine — minor updates]
Quick Fix:
[Exact commands to resolve critical issues]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

