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/ikarusmk/aicortex/rest-api-conventionsnpx skills add IkarusMK/AIcortex --skill rest-api-conventionsgit clone --depth 1 https://github.com/IkarusMK/AIcortexWhat 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 | $0.00026 | $0.00392 |
| Opus 5 | $0.00013 | $0.00196 |
| Sonnet 5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
rest-api-conventions 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.
What it actually says
REST API Conventions
When to use
Designing or reviewing an HTTP/JSON API.
Resources & methods
- Nouns, plural:
/orders,/orders/{id}/items. No verbs in paths. GETread (safe, idempotent) ·POSTcreate ·PUT/PATCHreplace/update ·DELETEremove.POSTfor non-CRUD actions:/orders/{id}/refund.
Status codes
200 ok · 201 created (+ Location) · 204 no content · 400 bad input ·
401 unauthenticated · 403 forbidden · 404 not found · 409 conflict ·
422 validation · 429 rate-limited · 5xx server. Don't return 200 with an error body.
Lists
- Paginate everything that can grow:
?limit=&cursor=(cursor) or?page=&per_page=. - Filtering/sorting via query params:
?status=open&sort=-created_at. - Return pagination metadata (total / next cursor) consistently.
Errors (one shape everywhere)
{ "error": { "code": "validation_error", "message": "…", "details": [ … ] } }
Also
- Version at the edge:
/v1/…. Don't break v1 in place. - Be consistent: same field casing, same date format (ISO 8601 UTC), same error shape.
- Make writes idempotent where clients may retry (idempotency keys).
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 · 37 lines · 26 tokens per session scan A 166ac54ecf06
rest-api-conventions is a skill published in the GitHub repository IkarusMK/AIcortex (9 stars, last pushed 13d ago), licensed Apache-2.0. It adds 26 tokens to every session and 392 once invoked, about $0.0001 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
MCP Server Builder
Step-by-step guidance for creating a new MCP server with FastMCP or the TypeScript SDK — tool definitions, resource handlers, error responses, and usage examples.
react-grab
Use when the user wants a hands-free loop where grabbing UI elements in the browser with React Grab feeds tasks to the agent automatically, with no copy-paste or manual handoff. Triggers: "watch react grab", "monitor my grabs", "auto-process react grab", "watch my clipboard for grabs". Not for a one-off paste of a…
fix-issues
Fix a batch of open GitHub issues end to end - one git worktree and one agent per issue (feature-dev for implementation, review-pr for review), individual PRs into develop, a release PR to main with a final multi-agent integration review, and optional tag/release/issue-comment publishing. Use when the user asks to…
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
promote
GitHub 截流。在同领域项目（local coding agent ↔ IM / mobile / remote console）的 feature-request issue 下，自动发现→起草→自我批判→护栏→（按 posture）发布 pikiloom 回复，并记录+度量。话术统一来自 promo/pitch.md；可由 promo/orchestrate.md 无人值守驱动。.
bzdesignprompt
为前端或网页设计任务选择并下载合适的 DESIGN.md 模板。当用户需要网页设计模板、UI 风格参考、设计系统、落地页或前端界面设计时，浏览长亭百智云 UI 设计模板库，根据产品场景和视觉偏好匹配模板，并将完整 DESIGN.md 保存到项目中。.