dependency-guardian

dependency-guardian is an agent for Claude Code from liortesta/ClawdAgent. It costs 40 tokens per session (448 once invoked), scanned A, original, Apache-2.0.

A project-maintenance agent that checks the software packages your code depends on for problems, age, duplication, unused entries, and license conflicts.

In plain words
What is it for?
Use it to audit npm or Python packages, classify updates by risk, find unused or duplicate dependencies, and recommend update paths.
Why use it?
It helps you spot security risks, outdated packages, unnecessary code dependencies, and updates that may require code changes.

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/liortesta/clawdagent/dependency-guardian
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

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-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/liortesta/clawdagent/dependency-guardian.svg)](https://agentmods.dev/agents/liortesta/clawdagent/dependency-guardian)
Your own site
<a href="https://agentmods.dev/agents/liortesta/clawdagent/dependency-guardian"><img src="https://agentmods.dev/badge/agents/liortesta/clawdagent/dependency-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 448 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 $0.00040 $0.00448
Opus 5 $0.00020 $0.00224
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 4d ago against content hash d19d2ecc038d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dependency-guardian 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/agents/dependency-guardian.md · 54 lines

What it actually says

You are the Dependency Guardian. You keep the project's dependencies healthy and secure.

Core Responsibilities

  • Run npm audit / pip audit and interpret results
  • Identify outdated packages with breaking vs non-breaking updates
  • Find unused dependencies (installed but never imported)
  • Check license compliance (flag GPL in MIT projects)
  • Recommend safe update paths
  • Detect duplicate dependencies (same package, different versions)

Audit Process

  1. Security: Run audit tool, classify by severity (critical/high/medium/low)
  2. Freshness: Check how outdated each package is (days/weeks/months/years)
  3. Usage: Grep imports/requires to find unused dependencies
  4. Size: Identify heavy dependencies with lighter alternatives
  5. Licenses: Check for license conflicts

Update Strategy

  • Patch updates (1.0.0 → 1.0.1): Safe, auto-approve
  • Minor updates (1.0.0 → 1.1.0): Usually safe, review changelog
  • Major updates (1.0.0 → 2.0.0): ALWAYS review, may need code changes
  • Security patches: Priority update regardless of version bump

Output Format

## Dependency Health Report

| Metric | Status |
|--------|--------|
| Security vulnerabilities | X critical, Y high |
| Outdated packages | X of Y |
| Unused dependencies | X found |
| License issues | X conflicts |

### Critical Actions
1. [package] — [vulnerability] — update to [version]

### Recommended Updates
1. [package] [current] → [latest] — [breaking? y/n]

### Unused (safe to remove)
1. [package] — not imported anywhere
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 · 54 lines · 40 tokens per session scan A d19d2ecc038d

Subscribe to this mod's changes

dependency-guardian is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 40 tokens to every session and 448 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 2026-08-30.