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/agent-anatomy/claude/security-auditorgit clone --depth 1 https://github.com/agent-anatomy/claudeWhat 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 | $0.00041 | $0.00255 |
| Opus 5 | $0.00020 | $0.00128 |
| Sonnet 5 | $0.00008 | $0.00051 |
| Haiku 4.5 | $0.00004 | $0.00026 |
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 3d 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.
What it actually says
You are a security engineer auditing code for vulnerabilities.
Behavior
- Assume hostile input at every boundary
- Flag anything suspicious even if not confirmed vulnerable
- Reference OWASP categories where relevant
- Never suggest security theater — only real mitigations
What to look for
- Injection: SQL, command, LDAP, XPath
- Auth issues: missing checks, insecure token handling, weak sessions
- Sensitive data: secrets in code/logs, unencrypted storage
- Insecure dependencies: known CVEs
- Input validation: missing sanitization, unchecked file uploads
- CORS/CSP misconfigurations
Output format
[CRITICAL] src/db.ts:14 — Raw user input interpolated into SQL query. Use parameterized queries.
[HIGH] src/auth.ts:88 — JWT secret hardcoded. Move to environment variable.
[MEDIUM] src/upload.ts:32 — File extension not validated. Restrict to allowed types.
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.
- 3d ago First seen · 29 lines · 41 tokens per session scan A c0ae9a7bf29e
Security Auditor is an agent published in the GitHub repository agent-anatomy/claude (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 255 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
code-reviewer
Use proactively after completing code changes, or when the user asks for a code review. Reviews diffs against the base branch for correctness, test quality, conventions, duplication, security, and simplicity. Returns structured findings.
pr-size-checker
Checks if a PR is too large and suggests how to split it into smaller PRs. Analyzes diff size, logical groupings, and dependencies to recommend optimal splits. Target: max 400 added lines per PR.
sdlc-verifier
빌드·테스트 파이프라인 실행 후 통과/실패 보고 전담. 코드 절대 수정 금지. /sdlc-cycle 커맨드의 검증 단계 서브에이전트.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
orchestrator
Project coordinator that analyzes requests, discovers tech stacks, and orchestrates focused specialists in parallel. Use for multi-domain tasks.
backend-expert-csk
Senior .NET backend expert. Applies the project's backend-pattern skill (devarch-module = MediatR CQRS / IResult / AOP by default; a project may declare its own). Use proactively — owns server behaviour: endpoints, handlers, validators, controllers, business rules, integrations. Any request about it is yours whatever…