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 skills/hautc-it/cil/securitynpx skills add hautc-it/cil --skill securitygit clone --depth 1 https://github.com/hautc-it/cilWhat 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 | $0.00059 | $0.01058 |
| Opus 5 | $0.00030 | $0.00529 |
| Sonnet 5 | $0.00012 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
security 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Design Skill
Project Context
Existing project
- Read
CLAUDE.md— security rules, compliance requirements, or auth decisions already made take priority. - Check the existing auth system — read the auth middleware, session/token handling, and permission checks already in place. Extend the existing pattern — never introduce a parallel auth mechanism.
- Check secret management — how does this project load secrets (env vars, vault, config file)? Match that approach; never add a new secret-loading method.
- Check dependency manifest — understand what security-relevant libraries are already in use (auth libraries, crypto, validators).
- Search memory —
memory_search("security auth [project] decision")— retrieve prior threat model decisions or known constraints. - Improving security incrementally within the existing posture is safer than replacing it wholesale.
Greenfield project
Security is cheapest to build in from the start — retrofitting it is expensive and error-prone:
- Do the threat model before writing any auth code — answer: who are the actors, what are the assets, where are the trust boundaries, what are the realistic attack vectors. Write the answers down; they become the security spec.
- Choose auth approach once — stateless token (no server state, harder to revoke) vs session (server state, easy revoke) vs platform credential (mobile/desktop keychain, OS identity). Pick based on deployment model and revocation requirements. Document it.
- Set secret management from day one — environment variables as the minimum floor; a dedicated secrets store for any cloud or team deployment. Never commit credentials, connection strings, or API keys.
- Define input validation strategy — validate at the boundary (API entry, UI input, file import), not deep inside business logic. Pick one validation approach and use it everywhere.
- Add dependency auditing to the build pipeline — use the standard audit tool for the platform. Integrate it from the first CI run; bolt-on tooling after 100 dependencies is painful.
- Write security decisions into
CLAUDE.md— auth approach, token lifetimes, where secrets live, validation approach. Makes them explicit and non-negotiable for all contributors. - Store the decisions:
memory_store("decision", "security: auth=[x], secrets=[x], validation=[x], dependency audit=[x]", ["security", "auth", "conventions"])
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 · 89 lines · 59 tokens per session scan A fdffada484a4
security is a skill published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,058 once invoked, about $0.0003 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 skills, from other repositories
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
golden-rss
Use when testing the rss golden build.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.