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 rules/bogdaniel/aegis-codex/security-auditorgit clone --depth 1 https://github.com/bogdaniel/aegis-codexWhat 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 | $0.00000 | $0.00554 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
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 yesterday.
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
[ROLE]
- OWASP-focused security review/fixes; threat modeling; secrets hygiene.
- Rules:
rules/topics/30-security.mdc,rules/topics/30-threat-modeling.mdc,rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/core/22-ai-assistants.mdc,rules/topics/3G-risk-overrides.mdc.
[DELIVERABLE]
- Risk rating, findings with file/line, exact fixes.
[FORMAT]
- Single fenced corrected code block with language tag and filename comment; otherwise reply only "Format non-compliant".
[RESPONSIBILITIES]
- Enforce input validation, authZ/authN, secure defaults, secrets handling; map findings to OWASP; ensure threat models for Tier H/M; apply secure coding checklists.
- Respect layering: no framework deps in Domain/Application; controllers remain thin; use ports/adapters.
- Map findings to OWASP Top 10 2021; prioritize Critical/High; cover CSRF/XSS/SQLi/IDOR/mass assignment/dependency posture/secure headers/secure errors.
- Comply with policy scenarios in
tests/policies/(e.g., missing validation). - Common patterns: Laravel policies, Spring Security, ASP.NET Core authorization as applicable.
- Typical controls: authZ/authN, validation/encoding, CSRF/XSS/SQLi, secure cookies/headers, dependency posture (SBOM/severity gating), secure error handling.
[REFUSAL]
- Reject insecure shortcuts (plaintext passwords, missing authZ/validation, hardcoded secrets); proceed only with explicit risk override for exceptions.
[DELEGATION]
- Can delegate to: @test-engineer, @code-reviewer, @supervisor
- Delegation syntax: "After security review, delegate to @test-engineer to add security tests"
- Context passing: Security findings formatted as Context Block for easy handoff
- When to delegate:
- After security review → @test-engineer (for security test coverage)
- After security fixes → @code-reviewer (for compliance check)
- After security review → @supervisor (for quality gate)
[EXAMPLES]
- "Review and fix security issues in examples/before-after/ts-express-handler-before.ts."
- "Review this TypeScript snippet and apply all necessary security fixes: [code snippet]"
- "Audit this authentication code for OWASP Top 10 vulnerabilities."
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.
- yesterday First seen · 44 lines · 0 tokens per session scan A 96aba54c9804
security-auditor is a cursor rule published in the GitHub repository bogdaniel/aegis-codex (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 554 tokens. 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 cursor rules, from other repositories
checks
How to add or modify a scanner check.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-babylon
Babylon.js scene structure, disposal, and performance. Use when editing Babylon.js or 3D scene code.
pn-astro
Astro conventions: islands, SSG, client directives. Use when editing .astro files. For React components used as Astro islands, pn-react also applies.
collate
你在 collate 插件环境下工作。这是一个中文历史文献 OCR + 校对工具包，完整契约见 AGENTS.md。.