Borrowing it
Nothing to install: this file belongs to starSumi/Sumi-Docs-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/starSumi/Sumi-Docs-MCP/main/.agents/skills/sumi-docs-use/SKILL.mdgit clone --depth 1 https://github.com/starSumi/Sumi-Docs-MCPWrote 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/starsumi/sumi-docs-mcp/sumi-docs-use)<a href="https://agentmods.dev/skills/starsumi/sumi-docs-mcp/sumi-docs-use"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs-mcp/sumi-docs-use/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/starsumi/sumi-docs-mcp/sumi-docs-use"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs-mcp/sumi-docs-use.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 | $0.00055 | $0.00623 |
| Opus 5 | $0.00028 | $0.00311 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
sumi-docs-use 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sumi-docs-use — 95% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Sumi Docs
Work from the repository root and read README.md plus the relevant page under
docs/ before running commands. Use Node.js 25.5.0 or newer and the pinned pnpm
version; do not substitute npm.
Select the workflow
- First checkout: run
pnpm install --frozen-lockfile,pnpm run build, thennode packages/mcp/dist/index.js doctor --json. - Default corpus: run
node packages/mcp/dist/index.js serve; repository discovery selects the reviewed rootdocs/corpus. - Another local corpus: pass its root-relative directory to
serveand add--openapi <relative-json-path>only when needed. - Published corpus: pass its HTTPS
_mcp/manifest URL and the human site URL through--base-url. - Remote MCP service: use
--transport streamable-http; keep the default loopback bind for development and apply the documented Host, Origin, TLS, and public-network gates before deployment. - Web development: run
pnpm --filter @sumi-labs/docs-web devand use the URL printed by Astro. - Agent host setup: read
docs/agent-hosts.md, build first, then use the checked-in project adapter for the active host.
Choose stdio for a local child process or Streamable HTTP for a remote MCP endpoint. Do not confuse either transport with the HTTPS corpus locator or the human page URL. Restart the server after source or configuration changes because a process keeps one read-only corpus snapshot.
Diagnose before changing configuration
Run doctor --json and inspect stderr separately from stdout. Prefer
repository-relative arguments and host project-root variables; do not commit
machine-specific absolute paths. Use --show-paths only for local diagnosis
and do not paste its output into public reports.
Confirm the active source with list_docs, then use search_docs and
fetch_doc with paths returned by the server. Do not claim semantic search,
live reload, source mutation, arbitrary Web crawling, or private-corpus
authorization.
For product usage, architecture, operations, and stable decision questions, query the active MCP projection before searching documentation files directly. For implementation changes, regressions, or current behavior, inspect source and tests because a process-local documentation snapshot can be stale. MCP constrains only its own read-only tool surface; host sandboxing and filesystem authorization remain the agent host's responsibility.
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.
- 11d ago First seen · 57 lines · 55 tokens per session scan A 96dac087b59e
sumi-docs-use is a skill published in the GitHub repository starSumi/Sumi-Docs-MCP (1 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 623 once invoked, about $0.0003 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
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
ocli-api
Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.
openapi-expert
Expert-level OpenAPI/Swagger specification for API design, documentation, and code generation. Use when the user mentions swagger, API specs, REST, API design, or documentation, or when the task involves OpenAPI Specification, Webhooks, or Polymorphism.
backend-openapi-documentation
Use this skill when the user says 'OpenAPI', 'Swagger', 'API documentation', 'spec-first', 'API spec', 'openapi.yaml', 'swagger.json', 'codegen', 'openapi-generator', 'API contract first'. This skill enforces spec-first API documentation with OpenAPI 3.x, code generation, and versioned specs. Applies to any backend…
api-documenter-v2
This public intake copy packages plugins/antigravity-awesome-skills/skills/api-documenter from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.
api-documentation-v2
API Documentation Workflow workflow skill. Use this skill when the user needs API documentation workflow for generating OpenAPI specs, creating developer guides, and maintaining comprehensive API documentation and the operator should preserve the upstream workflow, copied support files, and provenance before merging…