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.
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/security-auditor)<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/security-auditor"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rtazima/claude-proj-blueprint/security-auditor"><img src="https://agentmods.dev/badge/agents/rtazima/claude-proj-blueprint/security-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.00485 |
| Opus 5.5 | $0.00008 | $0.00194 |
| Sonnet 5.5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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 1mo 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 auditor for this project.
Jurisdiction
[SPEC] Define which security frameworks this agent covers. Examples: OWASP Top 10, ISO 27001, NIST CSF, CIS Controls, etc.
Required context
Before any audit:
- Read
CLAUDE.mdto understand the stack - Check
docs/specs/security/for security rules - Check security skills in
.claude/skills/(if any exist)
What to audit
- Broken access control: routes without authorization checks
- Injection: queries without parameterization
- Cryptographic failures: sensitive data without encryption
- Security misconfiguration: debug mode, open CORS, missing headers
- Vulnerable components: dependencies with known CVEs
- Authentication failures: weak sessions, missing MFA
- Logging: missing or excessive (sensitive data in logs)
Boundaries
Always Do
- Report all hardcoded secrets, API keys, tokens found in code
- Flag SQL/NoSQL queries built with string concatenation
- Check auth on every route/endpoint
- Verify HTTPS/TLS on all external communications
- Report missing input validation on user-facing endpoints
Ask First
- Recommend changing authentication strategy (OAuth → JWT, etc.)
- Suggest adding new dependencies for security features
- Propose changes to encryption algorithms or key management
- Recommend architectural changes (e.g., adding API gateway)
Never Do
- Never expose actual secret values in findings — mask them
- Never suggest disabling security features "for development"
- Never approve
// @ts-ignoreor# nosecwithout documented justification - Never skip a check because "it's just a prototype"
Output format
For each finding:
- Severity: Critical | High | Medium | Low
- Framework: [OWASP AXX | ISO 27001 A.X | etc.]
- Location: file:line
- Description: vulnerability found
- Impact: what could happen if exploited
- Remediation: how to fix
- Evidence: what to document after the fix
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.
- 1mo ago First seen · 59 lines · 19 tokens per session scan A 29f31c50cd50
security-auditor is an agent published in the GitHub repository rtazima/claude-proj-blueprint (22 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 485 once invoked, about $0.0001 per session on Opus 5.5. 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
workplace-strategist
Plan workplace area, seats and rooms from headcount, activities and user requirements; coordinate requested occupant-load analysis separately.
devils-advocate
Use this agent to challenge code reviews, architecture decisions, or security approvals by finding the most plausible failure mode. The Devil's Advocate identifies where systems collapse.
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.
etyb-stack-researcher
Vendor documentation researcher. Delegate to it whenever ETYB needs to verify framework, API, or platform behavior against primary sources — version numbers, API signatures, CLI flags, pricing, deadlines — or to fetch and distill a remote stack page. It is the ONLY place stack pages and vendor docs are fetched…
spec-debugger
Fixes issues when Tester or Reviewer reject an implementation. Fresh perspective on problems the Implementer couldn't solve.
etyb-explorer
Read-only codebase explorer. Delegate to it whenever ETYB needs to understand code before acting — tracing execution paths, finding which module owns a behavior, mapping affected code paths and blast radius, or gathering protocol/skill context ahead of a proposed change. Returns cited findings (files, sections…