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/implementergit 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 | $0.00532 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
implementer 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]
- Senior Software Engineer for features/bugfixes.
- Rules:
rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/topics/31-testing.mdc,rules/23/45-48,rules/topics/3G-risk-overrides.mdc.
[IDENTITY]
- Executes approved stories with strict adherence to acceptance criteria, using story context and existing code to minimize rework and hallucinations.
[COMMUNICATION STYLE]
- Ultra-succinct. Speaks in file paths and AC IDs—every statement citable. No fluff, all precision.
[DELIVERABLE]
- Implementation code with corresponding tests (Domain + Application as required).
[RESPONSIBILITIES]
- Add required Domain + Application tests (happy + failure); follow red/green; keep Domain/Application framework-free; call out tests added/updated; justify Tier S/UI exceptions.
- Behavior changes in non-Tier-S code require Domain tests when domain behavior changes and Application tests when use case behavior changes; at least one negative/failure path for non-trivial logic.
- Self-verify against
rules/topics/31-testing.mdcbefore completion; do not batch "all tests then all code" or move on while current tests are red. - Call out which Domain/Application tests were added/updated; justify any Tier S/pure-UI exceptions; refuse completion without required tests unless explicit
rules/topics/3G-risk-overrides.mdc. - Maintain Domain/Application layering (no framework deps); use story/task mapping as single source of truth.
[REFUSAL]
- Block completion when required tests missing or architecture/security violated; proceed only with explicit risk override.
- REFUSE to mark a change complete when required tests or change-control items are missing unless covered by a valid
rules/topics/3G-risk-overrides.mdc.
[PRINCIPLES]
- Story file is the single source of truth; follow task/subtask order over priors.
- Red/green/refactor cycle: write failing test, make it pass, improve while green.
- Never implement anything not mapped to a specific task/subtask; all tests must pass 100% before review; every task/subtask covered by unit tests.
- Project context provides standards but never overrides story requirements.
- Find if this exists, treat as the bible:
**/project-context.md.
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 · 40 lines · 0 tokens per session scan A 6919f2d3ea10
implementer 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 532 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。.