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 OutlineDriven/odin-claude-plugin --skill document-api-endpointgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/document-api-endpoint)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/document-api-endpoint"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/document-api-endpoint/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/outlinedriven/odin-claude-plugin/document-api-endpoint"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/document-api-endpoint.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 | $0.00040 | $0.00984 |
| Opus 5.5 | $0.00016 | $0.00394 |
| Sonnet 5.5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
document-api-endpoint 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.
This is a copy
100% identical to document-api-endpoint — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document and type an API endpoint
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to document, type, or fix OpenAPI schema for an endpoint whose generated spec drifts from its runtime response. |
| Authority | Reversible local: writes only the endpoint class and API documentation files for that one path; rollback is version control (revert to recover). No remote mutation. |
| Side effect | Updates or adds OpenAPI schema annotations and response types for one endpoint path. |
| Done | Endpoint has accurate schema annotations, typed responses matching runtime, and passing local schema validation. |
Inputs
- The endpoint route and HTTP method(s) to document, plus the serving class or handler (required).
- The runtime response shape: confirmed via a live request, a tool that calls the endpoint, or a test that exercises the path and captures the response (required).
- Optional: a request to promote the endpoint from a private or experimental status to public.
Procedure
- Confirm the endpoint's actual runtime response shape. Use a live request, an MCP or test tool that calls the endpoint, or a capturing test. Record the response keys, value types, and nesting. Done when: the serving class and its actual return shape are confirmed.
- Add or update OpenAPI schema annotations on the endpoint. Apply the framework's schema decorator or annotation mechanism (e.g.,
@extend_schema,@OpenApiResponse,ProducesResponseType) with operation ID, parameters, response codes, and examples. Reuse the project's existing parameter and example registries where they exist. Done when: the endpoint carries schema annotations with operation ID, parameters, responses, and examples. - Reconcile declared response types against the runtime response. Compare every key and type in the declared response type against the confirmed runtime shape. Correct the declared type to match runtime: counts returned as floats instead of integers, IDs declared as one type but emitted as another, nested types with the wrong field count. Reuse the canonical response type instead of re-declaring a copy; use optional-field mixins or partial schemas where the framework supports them. If the payload is proxied from another service and no clean canonical type exists, type it as a broad structure (
dict[str, Any]or equivalent) and confirm the shape from the owning service. Done when: every declared type matches the runtime response and no duplicate type copies remain. - Infer the response type from the producing code where possible. Do not use
castor# type: ignoreto force alignment; refactor the producing code so the type is inferred. Done when: the response type is inferred from producing code with no forced casts or ignores. - If a legacy schema definition (a hand-written JSON or YAML file for the path) exists, migrate every method on that path in one change: delete the legacy file and remove its reference from the top-level spec. Most generators do not merge hand-written and decorator-driven methods on the same path, so once any method uses schema annotations, all legacy methods on that path vanish from the generated spec. Done when: every method on the path is migrated and the legacy file and its reference are removed.
- Validate the generated OpenAPI specification locally. Run the project's schema generation command, the example validation command, the endpoint-specific test, and the lint or pre-commit check on the changed paths. Done when: all validation commands pass.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +1 lines aac30dce056d
- 1mo ago Changed · -23 tokens per session b4e50550a38e
- 1mo ago First seen · 43 lines · 63 tokens per session scan A 7ca252c02570
document-api-endpoint is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 40 tokens to every session and 984 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to document-api-endpoint, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…