Borrowing it
Nothing to install: this file belongs to starSumi/sumi-docs. 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/main/.agents/skills/sumi-docs-use/SKILL.mdgit clone --depth 1 https://github.com/starSumi/sumi-docsWrote 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/sumi-docs-use)<a href="https://agentmods.dev/skills/starsumi/sumi-docs/sumi-docs-use"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs/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/sumi-docs-use"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs/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 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.
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
95% identical to sumi-docs-use — 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 — 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.
- 3d ago Changed 96dac087b59e
- 11d ago First seen · 57 lines · 55 tokens per session scan A 35d6645dbc4c
sumi-docs-use is a skill published in the GitHub repository starSumi/sumi-docs (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. It is 95% identical to sumi-docs-use, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wordpress-plugin-to-emdash
Port a WordPress plugin to EmDash CMS. Use this skill when asked to migrate, convert, or port a WordPress plugin, theme functionality, or custom post type to EmDash. Provides concept mapping and implementation patterns.
review
Review one pull request for real bugs, regressions, and convention violations. Enumerate candidate issues across the whole diff, verify each against the code, then return structured line-anchored findings and a verdict. Read-only on GitHub; the orchestrator posts the review.
emdash-cli
Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
writing-emdash-docs
Write, revise, and review EmDash documentation for technical accuracy, useful structure, house style, and natural prose. Use when working on user documentation, guides, API reference pages, migration or upgrade guides, READMEs, contributor documentation, technical specifications, or release notes in the EmDash…
building-emdash-site
Build and customize EmDash CMS sites on Astro. Use when creating pages, defining collections, writing seed files, querying content, rendering Portable Text, setting up menus/taxonomies/widgets, configuring deployment, or any task involving an EmDash-powered Astro site. Assumes basic Astro knowledge but provides all…
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.