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/cosmix/loom/loom-api-documentationnpx skills add cosmix/loom --skill loom-api-documentationgit clone --depth 1 https://github.com/cosmix/loomWhat 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 | $0.00045 | $0.03674 |
| Opus 5 | $0.00023 | $0.01837 |
| Sonnet 5 | $0.00009 | $0.00735 |
| Haiku 4.5 | $0.00005 | $0.00367 |
Grade A, and why
loom-api-documentation scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.example.com/v2/users \ How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Documentation
Overview
Produce API docs developers can actually use: an accurate OpenAPI spec as the source of truth, plus reference/auth/error/versioning guides generated or kept in sync with it. Correctness and drift-prevention matter more than prose.
What every API must document
Auth · base URLs per environment · every endpoint + operation · request/response schemas · all response codes (incl. errors) · rate limits (with headers) · pagination · versioning/deprecation policy.
Spec-first vs code-first (choose deliberately)
| Approach | How | Drift risk | Use when |
|---|---|---|---|
| Spec-first | Hand-write OpenAPI, generate server stubs + clients + mocks | Runtime can diverge from spec unless validated | New APIs, contract negotiated across teams, mock-driven frontend |
| Code-first | Annotate handlers; framework emits spec (FastAPI, springdoc, drf-spectacular, tsoa) | Spec stays close to code, but annotations can lie | Existing codebase, small team, code is the truth |
Either way, enforce the contract in CI (lint + validate examples + breaking-change diff). Docs that aren't tested against the running API are fiction.
OpenAPI 3.1 — what changed from 3.0 (get these right)
- Fully aligned with JSON Schema 2020-12. A schema is now a valid JSON Schema; you can set
jsonSchemaDialectand use$schemaper-schema. nullable: trueis GONE. Use a type array:type: [string, "null"].- Type can be an array:
type: [string, integer]. exclusiveMinimum/exclusiveMaximumare numbers, not booleans (draft-4 behavior removed).- Top-level
webhooksdescribe events the API sends (see below). - Examples split by object: Schema Objects use JSON Schema's
examples(an array); Media Type / Parameter Objects useexample(singular) orexamples(a map of named Example Objects withsummary/value). Don't confuse the two. info.license.identifieraccepts an SPDX id (e.g.,MIT) instead of a URL.$refmay now sit alongside sibling keywords (e.g.,description).
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.
- 3d ago First seen · 334 lines · 45 tokens per session scan A 88960e64f901
loom-api-documentation is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 3,674 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Agent Design Principles
A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.
sandbox-next
Use when building or changing Cloudflare Sandbox apps on @cloudflare/sandbox@next (Sandbox SDK 1.0 preview)—code execution, AI runners, interpreters, CI-like jobs, terminals, files, mounts, tunnels, preview URLs, lifecycle, or errors. Not for the default stable package (use sandbox-stable) or for porting stable to…
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
turnstile-spin
Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's…
dag-factory
Authors Apache Airflow DAGs declaratively from dag-factory YAML configs. Use when building DAGs declaratively from YAML via dag-factory; creating/editing dag-factory templates/YAML configs,reating/editing dag-factory YAML configs, defaults, dynamic tasks, datasets, or callbacks; or validating dag-factory…
deploying-airflow
Deploys Airflow DAGs and projects. Use when deploying Airflow or answering anything about deployment - deploying DAGs/projects, pushing code, setting up CI/CD, deploying to production or deployment strategies for Airflow.