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 skills add hautc-it/cil --skill securitygit clone --depth 1 https://github.com/hautc-it/cilWrote 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/skills/hautc-it/cil/security)<a href="https://agentmods.dev/skills/hautc-it/cil/security"><img src="https://agentmods.dev/badge/skills/hautc-it/cil/security/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/skills/hautc-it/cil/security"><img src="https://agentmods.dev/badge/skills/hautc-it/cil/security.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 | $0.00059 | $0.01058 |
| Opus 5.5 | $0.00024 | $0.00423 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago 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 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,058 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
handoff
Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…
opik-evaluate
Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side…
opik
Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST). Use for "what span types exist", "how do I flush", "trackopenai", "add OpikTracer", "version a prompt". To instrument a repo end to end, use the opik-instrument skill.
glossary-init
USE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap / extend the repo's domain glossary. Surfaces candidate terms by identifier frequency, asks the user for 1-sentence definitions, writes GLOSSARY.md at repo root. Idempotent — re-running adds new…
hyper-plan
Use when about to start a non-trivial implementation that needs decomposition before coding. Also when the user invokes /hyperclaude:hyper-plan. Produces an ordered, bite-sized plan in .hyperclaude/plans/ — the input for /hyperclaude:hyper-plan-review and /hyperclaude:hyper-implement.
flow-create
Build a correct draft marketing scenario (flow) from a plain-language request: read the flows reference, resolve the entities the design needs to real ids, create and fill the blocks, wire the outputs, verify every block by reading it back, and hand over a link. Use when asked to create, build, assemble or set up a…