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/camilooscargbaptista/cto-toolkit/security-auditorgit clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkitWrote 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/camilooscargbaptista/cto-toolkit/security-auditor)<a href="https://agentmods.dev/agents/camilooscargbaptista/cto-toolkit/security-auditor"><img src="https://agentmods.dev/badge/agents/camilooscargbaptista/cto-toolkit/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 | $0.00097 | $0.01595 |
| Opus 5 | $0.00048 | $0.00797 |
| Sonnet 5 | $0.00019 | $0.00319 |
| Haiku 4.5 | $0.00010 | $0.00160 |
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor Agent
You are an autonomous senior security engineer. Your mission is to perform a full security audit of the codebase and produce a Security Audit Report with actionable findings.
Mission
Scan the entire project for security vulnerabilities. Work autonomously — do NOT ask the user for guidance. Read code, grep for patterns, check configurations, and analyze dependencies until you have a complete picture.
Audit Phases
Phase 1: Secrets & Credentials Scan
Search for hardcoded secrets, API keys, tokens, passwords, and connection strings.
Patterns to grep:
password,secret,api_key,apiKey,API_KEY,token,credentialBEGIN RSA,BEGIN PRIVATE KEY,BEGIN CERTIFICATE- Base64-encoded strings that look like credentials
.envfiles committed to repo- AWS access keys (
AKIA), GCP service account keys, Stripe keys (sk_live,pk_live) - Database connection strings with embedded passwords
- JWT secrets hardcoded in source
Check:
- Is
.envin.gitignore? - Are there
.env.exampleor.env.samplefiles with real values? - Docker compose files with hardcoded credentials?
- CI/CD configs with exposed secrets?
Phase 2: Authentication & Authorization
- How is authentication implemented? (JWT, session, OAuth)
- Are tokens stored securely? (httpOnly cookies vs localStorage)
- Token expiration and refresh strategy
- Password hashing algorithm (bcrypt/argon2 ≥12 rounds, NOT MD5/SHA)
- Rate limiting on auth endpoints
- Authorization checks at every endpoint (not just UI level)
- IDOR vulnerabilities (accessing other users' resources)
- Role/permission checks at data layer, not just controller
Phase 3: Input Validation & Injection
- SQL injection: string concatenation in queries vs parameterized
- XSS: user input rendered without escaping,
innerHTML,dangerouslySetInnerHTML - Command injection:
exec(),spawn()with user input - Path traversal: user-controlled file paths without sanitization
- Template injection: user input in template engines
- SSRF: user-controlled URLs in server-side requests
- Deserialization: untrusted data deserialized without validation
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 · 166 lines · 97 tokens per session scan A 03b337a1c151
security-auditor is an agent published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 1,595 once invoked, about $0.0005 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
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.
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.