audit-dependencies

audit-dependencies is a command for Claude Code from ParkerM2/create-claude-workflow. It costs 18 tokens per session (4,545 once invoked), scanned A, original, MIT.

A workflow for checking project dependencies, such as packages used by an application, for known security flaws, outdated versions, licence issues, and inactivity.

In plain words
What is it for?
Use it to audit Node.js, Python, Rust, Go, Java, Ruby, or PHP projects and track critical fixes through tickets and notifications.
Why use it?
It helps identify risky or neglected dependencies and records serious vulnerabilities for follow-up.

Command for Claude Code

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks shipped together

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 commands/parkerm2/create-claude-workflow/audit-dependencies
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

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 audit-dependencies

README.md
[![agentmods](https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/audit-dependencies.svg)](https://agentmods.dev/commands/parkerm2/create-claude-workflow/audit-dependencies)
Your own site
<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/audit-dependencies"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/audit-dependencies.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,545 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 $0.00018 $0.04545
Opus 5 $0.00009 $0.02273
Sonnet 5 $0.00004 $0.00909
Haiku 4.5 $0.00002 $0.00455

Measured 4d ago against content hash 4f0a3631968f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-dependencies 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.

.claude/commands/audit-dependencies.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Dependencies Workflow

Comprehensive dependency scanning for CVEs, outdated packages, license compliance, and staleness. Auto-creates Jira tickets for critical vulnerabilities with remediation guidance.

Integration Points

  • Jira MCP: Auto-create tickets for CVEs, link to tickets for tracking
  • GitHub Advisory Database: CVE lookup via web search/APIs
  • Package Managers: Native audit tools (npm, pip, cargo, etc.)
  • Memory: Audit history, dependency tracking, remediation status
  • Slack MCP: Vulnerability notifications

Workflow Phases

Phase 1: Project Detection (Type & Lock File Identification)

Identify project type and read dependency manifests:

  1. Detect Project Type

    • Check for manifest files in priority order:
      • Node.js: package.json + package-lock.json or yarn.lock
      • Python: requirements.txt, Pipfile, pyproject.toml + Pipfile.lock or poetry.lock
      • Rust: Cargo.toml + Cargo.lock
      • Go: go.mod + go.sum
      • Java: pom.xml (Maven) + pom.lock or build.gradle + gradle.lock
      • Ruby: Gemfile + Gemfile.lock
      • PHP: composer.json + composer.lock
    • Store detected type: memory/project-type.yaml
  2. Read Lock Files

    • Parse lock file for exact versions (not ranges from manifest)
    • Build dependency list:
      dependencies:
        express: 4.18.2 (direct)
        accepts: 1.3.8 (transitive)
        cookie: 0.5.0 (transitive)
      
    • Identify: direct vs. transitive (nested), pinned versions
  3. Monorepo Detection

    • If multiple package files: workspace/services/api/package.json, workspace/ui/package.json
    • Scan all: find . -name "package.json" -not -path "*/node_modules/*"
    • Flag: "Monorepo detected; scanning N independent projects"
    • Process each separately or aggregate (configurable)
  4. Extract Metadata

    • Project name, version, description
    • Dev vs. production dependencies (if available)
    • Private vs. public packages

Read the full file on GitHub · 547 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 · 547 lines · 18 tokens per session scan A 4f0a3631968f

Subscribe to this mod's changes

audit-dependencies is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 4,545 once invoked, about $0.0001 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.