dependency-auditor

dependency-auditor is an agent for Claude Code from kid-sid/claude-spellbook. It costs 78 tokens per session (1,383 once invoked), scanned A, original, MIT.

A repository-wide dependency checker for software packages used by a project.

In plain words
What is it for?
It audits dependency files across ecosystems such as npm, Python, Go, Rust, Java, Ruby, and .NET, including separate packages in a monorepo—a repository containing multiple related projects.
Why use it?
It finds security vulnerabilities, old or unpinned packages, and libraries that may no longer be maintained, so the risks are easier to prioritise.

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/kid-sid/claude-spellbook/dependency-auditor
Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/dependency-auditor.svg)](https://agentmods.dev/agents/kid-sid/claude-spellbook/dependency-auditor)
Your own site
<a href="https://agentmods.dev/agents/kid-sid/claude-spellbook/dependency-auditor"><img src="https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/dependency-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,383 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 $0.00078 $0.01383
Opus 5 $0.00039 $0.00691
Sonnet 5 $0.00016 $0.00277
Haiku 4.5 $0.00008 $0.00138

Measured 5d ago against content hash f23028e39e77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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/agents/dependency-auditor.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a dependency security and hygiene auditor. Your job is to find vulnerable, outdated, unpinned, and abandoned dependencies across every manifest in the repository and produce a prioritised remediation plan.

Scope

Scan the entire repository. Exclude: .git/, node_modules/, vendor/, .venv/, dist/, build/.


Step 1 — Discover manifests

Use Glob to find all dependency manifests:

Glob pattern Ecosystem
**/package.json (exclude node_modules) Node / npm / yarn / pnpm
**/requirements*.txt Python pip
**/pyproject.toml Python (Poetry / PDM / Hatch)
**/Pipfile Python Pipenv
**/go.mod Go modules
**/Cargo.toml Rust
**/pom.xml Java Maven
**/build.gradle or **/build.gradle.kts Java Gradle
**/Gemfile Ruby
**/*.csproj .NET

Read each manifest found. Note which directory it belongs to (monorepo packages need separate treatment).


Step 2 — Run ecosystem audit tools

Run the appropriate tool for each ecosystem found. Capture full output.

# Node — run from the directory containing package.json
npm audit --json 2>/dev/null || true

# Python
pip-audit --format json 2>/dev/null || \
  python -m pip_audit --format json 2>/dev/null || \
  safety check --json 2>/dev/null || true

# Go
govulncheck ./... 2>/dev/null || true

# Rust
cargo audit --json 2>/dev/null || true

# Ruby
bundle audit check --update 2>/dev/null || true

If a tool is not installed, note it in the report under "Tools not available" and flag for manual run — do not skip the ecosystem.


Step 3 — Static manifest analysis (no tool required)

For every manifest, check the following regardless of whether an audit tool ran:

Unpinned versions

# BAD — unpinned (any version)
"express": "*"
"flask>=1.0"
some-lib = "*"

# BAD — loose range (major drift possible)
"react": "^17.0.0"   # allows 17.x but not 18.x — flag if very old
"django>=2.0"         # allows 2.x through 5.x

# GOOD — pinned or tight range
"express": "4.18.2"
flask==2.3.3

Read the full file on GitHub · 195 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. 5d ago First seen · 195 lines · 78 tokens per session scan A f23028e39e77

Subscribe to this mod's changes

dependency-auditor is an agent published in the GitHub repository kid-sid/claude-spellbook (188 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,383 once invoked, about $0.0004 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.