dependency-audit

dependency-audit is a skill for Claude Code, Codex from srnichols/plan-forge. It costs 34 tokens per session (891 once invoked), scanned A, original, MIT.

A checklist for reviewing .NET project packages for known security vulnerabilities, outdated versions, and possible software-license conflicts. It also checks for leftover TODO or FIXME markers related to dependency changes.

In plain words
What is it for?
Use it to audit .NET dependencies, review transitive packages, identify packages that need upgrading, and flag license issues for human review.
Why use it?
It helps reveal risky or neglected dependencies before a pull request, after adding a package, or during regular maintenance.

Skill for Claude CodeCodex

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 skills/srnichols/plan-forge/dependency-audit
Any agent
npx skills add srnichols/plan-forge --skill dependency-audit
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/srnichols/plan-forge/dependency-audit.svg)](https://agentmods.dev/skills/srnichols/plan-forge/dependency-audit)
Your own site
<a href="https://agentmods.dev/skills/srnichols/plan-forge/dependency-audit"><img src="https://agentmods.dev/badge/skills/srnichols/plan-forge/dependency-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 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 $0.00034 $0.00891
Opus 5 $0.00017 $0.00445
Sonnet 5 $0.00007 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured yesterday against content hash 11593c0cfdf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dependency-audit 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 yesterday.

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.

presets/dotnet/.github/skills/dependency-audit/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency Audit Skill

Trigger

"Audit dependencies" / "Check for vulnerabilities" / "Are my packages up to date?"

Steps

1. Check for Known Vulnerabilities

dotnet list package --vulnerable --include-transitive

If this step fails (no .csproj found): Stop and report "No .NET project found in this directory."

2. Check for Outdated Packages

dotnet list package --outdated

3. Check for License Issues

dotnet list package --include-transitive --format json

Review output for any packages with restrictive licenses (GPL, AGPL) that conflict with your project license.

4. Completeness Scan

Use the forge_sweep MCP tool to check for TODO/FIXME markers that may have been left by prior dependency changes.

5. Review Findings

For each finding:

  • Critical/High CVE: Upgrade immediately or document accepted risk
  • Outdated (major version behind): Plan upgrade in next phase
  • Outdated (minor/patch): Update now if safe
  • License conflict: Flag for human review

6. Report

Dependency Audit Summary:
  🔴 Critical:     N vulnerabilities
  🟡 High:         N vulnerabilities
  🔵 Medium/Low:   N vulnerabilities

Outdated Packages:
  Major behind:    N (plan upgrade)
  Minor/Patch:     N (update now)

License Issues:    N
Sweep Markers:     N (TODO/FIXME from prior changes)

Overall: PASS / FAIL

Safety Rules

  • NEVER auto-upgrade major versions without human approval
  • ALWAYS check if the upgrade has breaking changes
  • Run dotnet test after any dependency change
  • Document any accepted vulnerabilities with justification

Temper Guards

Shortcut Why It Breaks
"These are all false positives" Dismissing findings without verification creates a blind spot. Each finding needs individual assessment.
"We'll update after the release" Post-release updates never happen. Vulnerable dependencies ship to production and stay there.
"Dev dependencies don't matter" Build-time dependencies can inject malicious code. Supply chain attacks target dev tooling.
"The vulnerability doesn't apply to our usage" Usage analysis requires proof. Document exactly which code paths are safe and why.

Read the full file on GitHub · 98 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. yesterday First seen · 98 lines · 34 tokens per session scan A 11593c0cfdf7

Subscribe to this mod's changes

dependency-audit is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 891 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 2026-09-03.