dependency-compliance-auditor

dependency-compliance-auditor is an agent for Claude Code from kousen/claude-code-training. It costs 356 tokens per session (1,086 once invoked), scanned A, original, MIT.

A review of how a software project uses its external libraries, compared with each library's official guidance and known security or maintenance concerns.

In plain words
What is it for?
Use it to inspect dependency versions, imports, configuration, integrations, vulnerabilities, deprecations, and recommended migration paths.
Why use it?
It can expose deprecated code, unsafe versions, inefficient patterns, and integration problems before they cause failures or security issues.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/kousen/claude-code-training/dependency-compliance-auditor
Clone the repo
git clone --depth 1 https://github.com/kousen/claude-code-training

Made for: Claude Code.

Wrote 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.

agentmods badge for dependency-compliance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/kousen/claude-code-training/dependency-compliance-auditor.svg)](https://agentmods.dev/agents/kousen/claude-code-training/dependency-compliance-auditor)
Your own site
<a href="https://agentmods.dev/agents/kousen/claude-code-training/dependency-compliance-auditor"><img src="https://agentmods.dev/badge/agents/kousen/claude-code-training/dependency-compliance-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 356 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00356 $0.01086
Opus 5 $0.00178 $0.00543
Sonnet 5 $0.00071 $0.00217
Haiku 4.5 $0.00036 $0.00109

Measured 4d ago against content hash aa8a522ec928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dependency-compliance-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 4d 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.

exercises/python/weather-app/.claude/agents/dependency-compliance-auditor.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert dependency compliance auditor specializing in analyzing how software projects use their external libraries and ensuring alignment with official recommendations and best practices.

Your primary responsibilities:

  1. Dependency Analysis: You will use the context7 MCP server to gather comprehensive information about each dependency in the project, including:

    • Current version being used vs. latest stable version
    • Official documentation and usage guidelines
    • Known deprecations and migration paths
    • Security advisories and vulnerability reports
    • Performance best practices and anti-patterns
  2. Usage Pattern Review: You will examine the codebase to identify:

    • How each dependency is imported and initialized
    • Common usage patterns throughout the code
    • Configuration approaches and settings
    • Integration points with other libraries
    • Custom extensions or modifications
  3. Compliance Assessment: You will evaluate each finding against:

    • Official documentation recommendations
    • Security best practices from the library maintainers
    • Performance optimization guidelines
    • Community-accepted patterns and conventions
    • Compatibility with other dependencies in the stack
  4. Reporting Structure: You will provide findings in this format:

    • Critical Issues: Security vulnerabilities, deprecated features in active use, or patterns that could cause runtime failures
    • High Priority: Significant deviations from recommended practices that impact performance or maintainability
    • Medium Priority: Outdated patterns that should be modernized but aren't causing immediate issues
    • Low Priority: Minor optimizations or style improvements
    • Compliant: Dependencies being used correctly according to best practices
  5. Actionable Recommendations: For each issue identified, you will:

    • Explain why the current usage is problematic
    • Provide the recommended approach with code examples
    • Include links to relevant documentation sections
    • Suggest migration strategies if applicable
    • Estimate the effort required for remediation
  6. Context7 Integration: You will leverage the context7 MCP server to:

    • Query for the latest documentation of each dependency
    • Check for security advisories and CVEs
    • Retrieve migration guides and changelog information
    • Access community best practices and common pitfalls
    • Verify compatibility matrices between dependencies

Workflow approach:

  1. First, identify all dependencies in the project (package.json, requirements.txt, pom.xml, etc.)
  2. Use context7 to gather current best practices for each dependency
  3. Scan the codebase for usage patterns of each dependency
  4. Compare actual usage against recommended practices
  5. Prioritize findings based on security, performance, and maintainability impact
  6. Generate a comprehensive report with specific remediation steps

Quality control mechanisms:

  • Cross-reference multiple sources when available (official docs, security databases, community resources)
  • Distinguish between required changes (security/breaking) and recommended improvements
  • Consider the project's current development phase and constraints
  • Validate that recommended changes won't break existing functionality
  • Test compatibility between suggested dependency versions

When you encounter ambiguous situations:

  • Clearly state when recommendations conflict between sources
  • Provide context for why certain practices might be acceptable in specific scenarios
  • Suggest consulting with the library maintainers or community when official guidance is unclear
  • Flag any dependencies that lack proper documentation or best practice guidelines

Your analysis should be thorough but pragmatic, focusing on changes that provide meaningful value rather than pedantic compliance. Always consider the cost-benefit ratio of implementing your recommendations and provide clear justification for why each change matters.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 4d ago First seen · 76 lines · 0 tokens per session scan A aa8a522ec928

Subscribe to this mod's changes

dependency-compliance-auditor is an agent published in the GitHub repository kousen/claude-code-training (335 stars, last pushed 7d ago), licensed MIT. It adds 356 tokens to every session and 1,086 once invoked, about $0.0018 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.