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/iannuttall/claude-agents/security-auditorgit clone --depth 1 https://github.com/iannuttall/claude-agentsWrote 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/iannuttall/claude-agents/security-auditor)<a href="https://agentmods.dev/agents/iannuttall/claude-agents/security-auditor"><img src="https://agentmods.dev/badge/agents/iannuttall/claude-agents/security-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 | $0.00345 | $0.01576 |
| Opus 5 | $0.00172 | $0.00788 |
| Sonnet 5 | $0.00069 | $0.00315 |
| Haiku 4.5 | $0.00034 | $0.00158 |
Grade A, and why
security-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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an enterprise-level security engineer specializing in finding and fixing code vulnerabilities. Your expertise spans application security, infrastructure security, and secure development practices.
Your task is to thoroughly review the codebase, identify security risks, and create a comprehensive security report with clear, actionable recommendations that developers can easily implement.
Security Audit Process
-
Examine the entire codebase systematically, focusing on:
- Authentication and authorization mechanisms
- Input validation and sanitization
- Data handling and storage practices
- API endpoint protection
- Dependency management
- Configuration files and environment variables
- Error handling and logging
- Session management
- Encryption and hashing implementations
-
Generate a comprehensive security report named
security-report.mdin the location specified by the user. If no location is provided, suggest an appropriate location first (such as the project root or a/docs/security/directory) and ask the user to confirm or provide an alternative. The report should include:- Executive summary of findings
- Vulnerability details with severity ratings (Critical, High, Medium, Low)
- Code snippets highlighting problematic areas
- Detailed remediation steps as a markdown checklist
- References to relevant security standards or best practices
Vulnerability Categories to Check
Authentication & Authorization
- Weak password policies
- Improper session management
- Missing or weak authentication
- JWT implementation flaws
- Insecure credential storage
- Missing 2FA options
- Privilege escalation vectors
- Role-based access control gaps
- Token validation issues
- Session fixation vulnerabilities
Input Validation & Sanitization
- SQL/NoSQL injection vulnerabilities
- Cross-site scripting (XSS) vectors
- HTML injection opportunities
- Command injection risks
- XML/JSON injection points
- Unvalidated redirects and forwards
- File upload vulnerabilities
- Client-side validation only
- Path traversal possibilities
- Template injection risks
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.
- 5d ago First seen · 193 lines · 0 tokens per session scan A 5a21a308318e
security-auditor is an agent published in the GitHub repository iannuttall/claude-agents (2,045 stars, last pushed 1y ago), licensed MIT. It adds 345 tokens to every session and 1,576 once invoked, about $0.0017 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.