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 skills/alirezarezvani/claude-code-tresor/dependency-auditornpx skills add alirezarezvani/claude-code-tresor --skill dependency-auditorgit clone --depth 1 https://github.com/alirezarezvani/claude-code-tresorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alirezarezvani/claude-code-tresor/dependency-auditor)<a href="https://agentmods.dev/skills/alirezarezvani/claude-code-tresor/dependency-auditor"><img src="https://agentmods.dev/badge/skills/alirezarezvani/claude-code-tresor/dependency-auditor.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00051 | $0.01331 |
| Opus 5 | $0.00026 | $0.00665 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
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 6d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Auditor Skill
Automatic dependency vulnerability checking.
When I Activate
- ✅ package.json modified
- ✅ requirements.txt changed
- ✅ Gemfile or pom.xml modified
- ✅ User mentions dependencies or vulnerabilities
- ✅ Before deployments
- ✅ yarn.lock or package-lock.json changes
What I Check
Dependency Vulnerabilities
- Known CVEs in packages
- Outdated dependencies with security fixes
- Malicious packages
- License compatibility issues
- Deprecated packages
Package Managers Supported
- Node.js: npm, yarn, pnpm
- Python: pip, pipenv, poetry
- Ruby: bundler
- Java: Maven, Gradle
- Go: go modules
- PHP: composer
Example Alerts
NPM Vulnerability
# You run: npm install lodash
# I automatically audit:
🚨 HIGH: Prototype Pollution in lodash
📍 Package: [email protected]
📦 Vulnerable versions: < 4.17.21
🔧 Fix: npm update lodash
📖 CVE-2020-8203
https://nvd.nist.gov/vuln/detail/CVE-2020-8203
Recommendation: Update to [email protected] or higher
Python Vulnerability
# You modify requirements.txt: django==2.2.0
# I alert:
🚨 CRITICAL: Multiple vulnerabilities in Django 2.2.0
📍 Package: [email protected]
📦 Vulnerable versions: < 2.2.28
🔧 Fix: Update requirements.txt to Django==2.2.28
📖 CVEs: CVE-2021-33203, CVE-2021-33571
Affected: SQL injection, XSS vulnerabilities
Recommendation: Update immediately to [email protected]+
Multiple Vulnerabilities
# After npm install:
🚨 Dependency audit found 8 vulnerabilities:
- 3 CRITICAL
- 2 HIGH
- 2 MEDIUM
- 1 LOW
Critical issues:
1. [email protected] - SSRF vulnerability
Fix: npm install axios@latest
2. [email protected] - Prototype pollution
Fix: npm install ajv@^8.0.0
3. [email protected] - Information disclosure
Fix: npm install node-fetch@^2.6.7
Run 'npm audit fix' to automatically fix 6/8 issues
Automatic Actions
On Dependency Changes
1. Detect package manager (npm, pip, etc.)
2. Run security audit command
3. Parse vulnerability results
4. Categorize by severity
5. Suggest fixes
6. Flag breaking changes
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 252 lines · 51 tokens per session scan A a24f8c38f61b
dependency-auditor is a skill published in the GitHub repository alirezarezvani/claude-code-tresor (769 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,331 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
verify
Run Forge's canonical verification chain (format:check + lint + typecheck + build + test). Use before claiming any task complete or opening a PR.
add-provider
Scaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked transport.
add-tool
Scaffold a new Forge tool end-to-end — implementation, registration, permission/risk metadata, sandbox routing, and a unit test.
flywheel
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
idea-wizard
30 → 5 → 15 funnel for brainstorming new features on the existing Forge codebase. Use when adding capability to a mature install, not for greenfield.
plan-synthesize
Synthesize competing plans from multiple frontier models into a single best-of-all-worlds hybrid. Use after /plan has produced 2+ competing plans in .flywheel/plans/.