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/sannnao/react-docs-mcp/add-docs-presetnpx skills add Sannnao/react-docs-mcp --skill add-docs-presetgit clone --depth 1 https://github.com/Sannnao/react-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/sannnao/react-docs-mcp/add-docs-preset)<a href="https://agentmods.dev/skills/sannnao/react-docs-mcp/add-docs-preset"><img src="https://agentmods.dev/badge/skills/sannnao/react-docs-mcp/add-docs-preset.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01789 |
| Opus 5 | $0.00035 | $0.00894 |
| Sonnet 5 | $0.00014 | $0.00358 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
add-docs-preset 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 5d 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.
initialize → tools/list (names/enums correct) → `search_<lib>_docs` (results have live-site URLs) → `get_doc` for a nested AND a root-level path → `list_sections` → a bogus `section` (must return the validation error lis How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a new docs MCP package
A new docs server = one preset file + a thin package scaffold on the shared engine. Existing examples: src/presets/reactDocs.ts (root package), src/presets/reactNativeDocs.ts + packages/react-native-docs-mcp/ (versioned docs), src/presets/reactHookFormDocs.ts + packages/react-hook-form-docs-mcp/ (simplest case — copy this one as your template).
1. Feasibility check — NEVER skip
The engine requires a git repo containing markdown/MDX docs. Rendered-HTML-only docs sites don't fit — stop and say so.
Shallow-clone the candidate repo into the scratchpad (never into this project) and determine:
- Content root: where do the actual doc files live? Don't guess — grep the site config (Docusaurus
docs: { path: ... }in docusaurus.config.*, contentlayer.config.ts, astro/nextra config). react.dev usessrc/content, react-native-website uses rootdocs/, react-hook-form usessrc/content. - File mix: count
.mdvs.mdx(both supported). Check for_-prefixed partial files (auto-excluded by the glob). - Sections: which subfolders of the content root are real sections vs flat files? Only real subfolders go in
sections(the server filters to existing dirs at runtime anyway). - Frontmatter
idoverrides (the RN lesson — this caused real wrong-URL bugs):grep -rn "^id:"in the content root. If files set aniddiffering from their filename, Docusaurus-style sites route by id → setuseFrontmatterId: true. Verify 2-3 sample URLs against the live site either way; a valid-looking URL scheme that 404s or serves the wrong page is the failure mode to catch here. - Versioned docs: is there a
versioned_docs/-style folder? Only then does the package need a--docs-versionflag (copy the pattern frompackages/react-native-docs-mcp/src/index.ts, including version-format validation).
Also: npm view <lib>-docs-mcp version must 404 (name unclaimed).
2. Preset file: src/presets/<lib>Docs.ts
Copy reactHookFormDocs.ts. Rules:
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.
- 5d ago First seen · 81 lines · 70 tokens per session scan A 508e164b3b46
add-docs-preset is a skill published in the GitHub repository Sannnao/react-docs-mcp (8 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,789 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
using-react-native-docs-mcp
How to effectively use the react-native-docs-mcp search and doc-retrieval tools instead of relying on training-data memory of React Native APIs.
cc-workflow-ai-editor
AI workflow editor for CC Workflow Studio. Create and edit visual AI agent workflows through interactive conversation using MCP tools (getworkflowschema, getcurrentworkflow, applyworkflow). Use when the user wants to create a new workflow, modify an existing workflow, or edit the workflow canvas in CC Workflow Studio…
technical-design-doc-creator
Creates comprehensive Technical Design Documents (TDD) following industry standards with mandatory sections, optional sections, and interactive gathering of missing information.
tlc-spec-driven
Project and feature planning with 4 phases - Specify, Design, Tasks, Implement+Validate. Creates atomic tasks with verification criteria and maintains persistent memory across sessions. Stack-agnostic. Use when (1) Starting new projects (initialize vision, goals, roadmap), (2) Working with existing codebases (map…
coding-guidelines
Apply when writing, modifying, or reviewing code. Behavioral guidelines to reduce common LLM coding mistakes. Triggers on implementation tasks, code changes, refactoring, bug fixes, or feature development.
video-editing
Operate Video Agent Runtime projects through structured MCP tools for transcript-first long-form-to-short-form editing, preview review, feedback diagnosis, narration, versioning, and approved export. Use for editing an existing runtime project; do not use for direct FFmpeg or manual project-JSON changes.