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 commands/zevtos/agentpipe/auditgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00028 | $0.00805 |
| Opus 5 | $0.00014 | $0.00402 |
| Sonnet 5 | $0.00006 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
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 2d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a comprehensive security audit. This goes deeper than a code review — it includes threat modeling, architecture-level analysis, and dependency auditing.
Context
@CLAUDE.md
Audit Scope
$ARGUMENTS
Pipeline
Step 1: Reconnaissance
Before invoking any agent, map the attack surface:
- Identify all entry points (API endpoints, WebSocket handlers, webhooks, file uploads)
- Identify sensitive data flows (auth tokens, PII, financial data, keys)
- Identify third-party integrations and trust boundaries
- Check for existing security controls (auth middleware, validation, rate limiting)
- List all dependencies with versions
Present the attack surface map to the user.
Step 2: Security Audit (Security Agent)
Run the security agent with the full scope:
"Perform a comprehensive security audit of this project.
Scope: $ARGUMENTS (if empty, audit the entire project)
Attack surface: [paste from Step 1]
Execute the full audit methodology:
- STRIDE threat model on the architecture
- OWASP Top 10:2025 checklist against the codebase
- OWASP API Security Top 10:2023 if this is an API
- Authentication and authorization flow review
- Cryptographic implementation review (if applicable)
- Input validation and output encoding review
- Error handling and information leakage review
- Session management review
- Security header audit
- Secret management audit (scan for hardcoded credentials)"
Step 3: Dependency Audit
Run dependency scanning:
# Run available scanners
npm audit 2>/dev/null || pip-audit 2>/dev/null || cargo audit 2>/dev/null || true
If Trivy is available: trivy fs --severity CRITICAL,HIGH .
Cross-reference findings with:
- CISA KEV catalog (is any CVE actively exploited?)
- EPSS scores (what's the exploitation probability?)
Step 4: Architecture Review (Architect Agent — security focus)
Run the architect agent:
"Review this system architecture from a SECURITY perspective only:
- Are trust boundaries correctly placed?
- Are service-to-service communications authenticated (mTLS, API keys)?
- Is the principle of least privilege followed for database access?
- Are there single points of failure in the auth chain?
- Is sensitive data encrypted at rest and in transit?
- Is there proper network segmentation?"
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.
- 2d ago First seen · 111 lines · 28 tokens per session scan A 49395f6fc248
audit is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 805 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.