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/using-react-native-docs-mcpnpx skills add Sannnao/react-docs-mcp --skill using-react-native-docs-mcpgit clone --depth 1 https://github.com/Sannnao/react-docs-mcpWhat 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 | $0.00038 | $0.00426 |
| Opus 5 | $0.00019 | $0.00213 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
using-react-native-docs-mcp 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 2d 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:
- using-react-native-docs-mcp — 100% identical, 0 lines differ
What it actually says
Using react-native-docs-mcp
When this MCP server is connected, prefer it over recalling React Native APIs from memory — training data goes stale, this tool indexes the live official docs.
Workflow
- Search first. Call
search_react_native_docswith a natural-language query before writing React Native code that touches an API you're not 100% certain about. Results include a relevance-ranked snippet and aurl. - Drill in only when needed. If the search snippet isn't enough, call
get_docwith thepathfrom a search result. It returns a ~1500 char summary plus a structure outline by default — enough for most questions. - Use
full: truesparingly. Passfull: truetoget_doconly when the summary likely cuts off something you need — New Architecture migration guides, native-module walkthroughs, or anything with many sequential steps. Don't default tofullfor every call; it costs more context for no benefit on short reference pages. - Search unfiltered by default. Most React Native docs pages live flat with no section; only
the-new-architecture,legacy, andreleasesare real sections. Use thesectionfilter only when specifically targeting one of those areas. - Pin docs to the user's actual version when it matters. If the project's installed
react-nativeversion differs from latest and the question involves an API that may have changed across versions, note that the server can be started with--docs-version=X.YYto index that release's frozen docs snapshot — mention this to the user rather than silently assuming latest-version behavior applies to their older app. - Refresh if docs seem stale. Call
update_docsto pull the latest commit before concluding an API doesn't exist.
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.
- 2d ago First seen · 18 lines · 38 tokens per session scan A b322b9cff6a8
using-react-native-docs-mcp is a skill published in the GitHub repository Sannnao/react-docs-mcp (8 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 426 once invoked, about $0.0002 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
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.
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
argent-settings-permissions
Grant, deny, or reset an app's runtime permissions (camera, microphone, photos, contacts, notifications, calendar, location, location-always, media-library, motion, reminders) on an iOS simulator or Android device using the argent settings-permissions tool - without navigating the system Settings UI. Use when the…
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.