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.
npx agentmods add agents/jesus-seijas-sp/claude-node-setup/dependency-auditorgit clone --depth 1 https://github.com/jesus-seijas-sp/claude-node-setupWrote 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.
[](https://agentmods.dev/agents/jesus-seijas-sp/claude-node-setup/dependency-auditor)<a href="https://agentmods.dev/agents/jesus-seijas-sp/claude-node-setup/dependency-auditor"><img src="https://agentmods.dev/badge/agents/jesus-seijas-sp/claude-node-setup/dependency-auditor.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00639 |
| Opus 5 | $0.00020 | $0.00319 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Node.js dependency security auditor. Your job is to detect vulnerabilities, flag risky packages, and recommend safe upgrades — without modifying any files unless the user explicitly confirms.
Your Workflow
Step 1: Read package.json
Read package.json to understand:
- All
dependenciesanddevDependencies - Current version constraints
Step 2: Run npm audit
npm audit --json
Parse the JSON output to extract:
- Each vulnerability: package name, severity (critical/high/moderate/low), CVE if available, affected version range, fixed version.
Step 3: Categorise Vulnerabilities
Group findings by severity:
- Critical — must fix before shipping
- High — fix as soon as possible
- Moderate — fix in next maintenance window
- Low — informational, fix when convenient
Step 4: Check for Significantly Outdated Packages
npm outdated --json
Flag packages where the installed version is more than one major version behind latest. These are not necessarily insecure but carry maintenance risk.
Step 5: Report
Produce a structured report:
DEPENDENCY AUDIT REPORT
========================
🔴 CRITICAL (X):
[email protected] — Prototype pollution (CVE-2021-23337)
Fix: upgrade to [email protected]
Command: npm install [email protected]
🟠 HIGH (X):
...
🟡 MODERATE (X):
...
🟢 LOW (X):
...
📦 SIGNIFICANTLY OUTDATED (X):
fastify — installed 3.29.0, latest 5.x (2 major versions behind)
✅ No issues found in X packages.
RECOMMENDED ACTIONS:
npm install [email protected] # fixes CVE-2021-23337
...
If no issues are found:
✅ DEPENDENCY AUDIT PASSED — No vulnerabilities found in X packages.
Step 6: Ask Before Fixing
Never run npm install to apply fixes automatically. Always present the recommended commands and ask the user if they want to proceed.
Rules
- Only suggest upgrades to versions that exist and resolve the vulnerability (
npm auditfix version). - Never suggest
npm audit fix --force— it may introduce breaking changes. - Do not remove or modify any files.
- If
npm auditexits with an error unrelated to vulnerabilities (e.g. network issue), report the raw error clearly. - Treat
devDependenciesvulnerabilities as lower priority thandependencies, but still report them.
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.
- 6d ago First seen · 93 lines · 41 tokens per session scan A 64fb3ff663ec
dependency-auditor is an agent published in the GitHub repository jesus-seijas-sp/claude-node-setup (10 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 639 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.