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/api-designnpx skills add hautc-it/cil --skill api-designgit 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 | $0.00047 | $0.01092 |
| Opus 5 | $0.00023 | $0.00546 |
| Sonnet 5 | $0.00009 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
api-design 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: API Design
A public contract is forever. Cheap to add a field; impossible to remove one.
Project Context
Existing project
- Read
CLAUDE.md— API conventions, versioning rules, or auth patterns already decided take priority. - Check existing routes — read 2–3 existing endpoints. Match their URL structure, naming convention, HTTP method usage, and response envelope shape.
- Find the error format — search for existing error responses. Use the exact same shape — never introduce a second error schema.
- Check auth middleware — how is authentication done in existing routes? Apply the same pattern (middleware, guard, decorator) — don't invent a new one.
- Check pagination — does the project already use cursor or offset pagination? Don't mix styles.
- Search memory —
memory_search("api design [resource] convention")— retrieve prior decisions on versioning, naming, or error format. - Consistency with the established contract beats theoretical perfection.
Greenfield project
No API exists yet — you are setting the contract others will depend on:
- Choose transport — use the Decision table below. Default to REST unless there's a concrete reason not to.
- Define the error shape once — write it down before the first endpoint. Every endpoint returns this exact shape — no exceptions.
- Set versioning strategy — pick one approach (URL prefix, header, or media type) and document it in
CLAUDE.md. Don't let each endpoint invent its own. - Decide auth approach — stateless token, session, or API key. Pick one that matches the deployment model. Document token lifetime and refresh/revocation strategy.
- Set pagination style — cursor-based for any collection that grows; offset only for truly static or small data. Mixing styles later is a breaking change.
- Write
CLAUDE.mdentries for each decision so contributors don't re-litigate them. - Store the decisions:
memory_store("decision", "api: transport=[x], error shape=[x], versioning=[x], auth=[x], pagination=[x]", ["api", "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.
- 2d ago First seen · 86 lines · 47 tokens per session scan A 1652913e1b39
api-design is a skill published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,092 once invoked, about $0.0002 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.
git-rollback
Interactively rollback Git branch to historical version; lists branches, versions, then executes reset/revert after confirmation.
golden-rss
Use when testing the rss golden build.
design-system-builder
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
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.
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…