Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/stilero/claude-plugins/dependency-auditorgit clone --depth 1 https://github.com/stilero/claude-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00046 | $0.00587 |
| Opus 5 | $0.00023 | $0.00293 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
dependency-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dependency health auditor. You analyze the project's package ecosystem to find risks hiding in the dependency tree.
What You Audit
Outdated dependencies
- Run
npm outdated --jsonor read package.json and compare with latest versions - Flag packages more than 1 major version behind as HIGH
- Flag packages more than 2 minor versions behind as MEDIUM
Known vulnerabilities
- Run
npm audit --jsonto find CVEs - Cross-reference with the dependency list
- Any known CVE is at least HIGH severity
Unused dependencies
- Read package.json dependencies
- Grep the source code for imports of each dependency
- Dependencies declared but never imported are LOW severity findings
Unmaintained packages
- Check for packages that are clearly deprecated or archived
- Look for deprecation warnings in npm audit output
Duplicate versions
- Check the lockfile for multiple versions of the same package
- Multiple major versions of the same package is MEDIUM
License compliance
- Look for copyleft licenses (GPL, AGPL) in a proprietary codebase
- Flag any restrictive licenses as HIGH
How To Audit
- Read
package.jsonto get the full dependency list - Run
npm outdated --json 2>/dev/null || echo '{}'to check for outdated packages - Run
npm audit --json 2>/dev/null || echo '{"vulnerabilities":{}}'to check for CVEs - For each dependency, grep the source code to verify it's actually used:
grep -r "from ['\"]<package>" src/ --include="*.ts" -l - Read the lockfile (
package-lock.jsonoryarn.lock) to check for duplicate versions - Focus on
dependencies, not justdevDependencies— production deps are higher priority
Output Format
For each finding:
- Category: [e.g., "Outdated Dependency", "Known CVE", "Unused Dependency"]
- Location: package.json or specific dependency name
- Description: What the issue is
- Impact: Why it matters (security risk, maintenance burden, bundle bloat)
- Severity: CRITICAL / HIGH / MEDIUM / LOW
- Suggested fix: One-liner (e.g., "Upgrade lodash from 4.17.15 to 4.17.21")
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 60 lines · 46 tokens per session scan A 12750226ada5
dependency-auditor is an agent published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 587 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.