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 GetStream/agent-skills --skill stream-react-nativegit clone --depth 1 https://github.com/GetStream/agent-skillsWrote 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/getstream/agent-skills/stream-react-native)<a href="https://agentmods.dev/skills/getstream/agent-skills/stream-react-native"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-react-native/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/getstream/agent-skills/stream-react-native"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-react-native.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 24 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 25 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 28 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 29 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00244 | $0.07882 |
| Opus 5.5 | $0.00098 | $0.03153 |
| Sonnet 5.5 | $0.00049 | $0.01576 |
| Haiku 4.5 | $0.00024 | $0.00788 |
Grade A, and why
stream-react-native 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 23d 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.
Bash(curl -Ls https://getstream.io/chat/docs/sdk/react-native/llms.txt), How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream React Native - skill router + execution flow
Rules: Read RULES.md once per session. Every non-negotiable React Native Chat, Video, and Feeds rule is stated there.
This file is the single entrypoint: intent classification, product selection, project detection, and module pointers for Stream Chat React Native, Stream Video React Native, and Stream Feeds React Native work.
Step 0: Intent classifier (mandatory first - never skip)
Before any tool call, decide the track from the user's input alone. Do not probe the filesystem first.
Signals -> track
| Signal in user input | Track |
|---|---|
| "Build/create/scaffold a new React Native app", "create an Expo app", "new Stream Chat RN app", "new Stream Video RN app", "new Stream Feeds RN app", empty directory + React Native/Expo Chat / Video / Feeds | A - New app |
| "Upgrade/migrate/bump a Stream SDK version", "upgrade stream-chat-react-native to v9", "migrate Chat RN to the new SDK", "v8 to v9", "bump Stream Video/Feeds", "Feeds v2 -> v3" | M - Migrate / upgrade |
"Migrate from Sendbird", "replace Sendbird with Stream", "we're switching off Sendbird", "rip out @sendbird/uikit-react-native", "convert SendbirdUIKitContainer / createGroupChannelFragment to Stream", @sendbird/chat / @sendbird/uikit-react-native / -foundation present in the target's package.json |
S - Migrate from Sendbird |
| "Add/integrate Stream Chat into this app", "wire Chat RN", "set up stream-chat-expo", "add a video call", "wire Stream Video", "set up @stream-io/video-react-native-sdk", "add an activity feed", "wire Stream Feeds", "set up @stream-io/feeds-react-native-sdk", "change/customize this Chat / Video / Feeds UI" | B - Existing app |
React Native, Expo, Expo Router, stream-chat-react-native, stream-chat-expo, @stream-io/video-react-native-sdk, @stream-io/feeds-react-native-sdk, Stream Chat RN, Stream Video RN, Stream Feeds RN, Chat React Native, Video React Native, Feeds React Native, migration |
C - Reference lookup if the user only asks how/docs; otherwise B - Existing app |
Explicit product/runtime token: Chat React Native, Chat Expo, Video React Native, Video Expo, Feeds React Native, Feeds Expo |
C - Reference lookup |
| Words "docs" or "documentation" around Stream Chat, Stream Video, or Stream Feeds React Native / Expo work | C - Reference lookup |
| "How do I {X} in React Native/Expo?", "What does {SDK component/hook/prop} do?" | C - Reference lookup |
| "Audit/review/check an existing Stream Video integration against best practices", "is my video app production-ready?", "what am I missing before launch?" | C - Reference lookup (read-only) - run the Integration best-practices audit in references/VIDEO-REACT-NATIVE.md |
| "Install Stream packages", "set up Chat RN", "set up Video RN", "set up Feeds RN", "wire auth/token flow" with no broader feature request | D - Bootstrap / setup |
"Build a ChatGPT-style app", "add an AI assistant / support bot / copilot", "stream the LLM response", "thinking indicator", "stop generating", "voice input to the AI", "let the agent do X on the device", LangChain, Vercel AI SDK, @stream-io/chat-react-native-ai |
A (new app) or B (existing app), then run ai-integration.md for the integration step; C if the user only asks how one AI component works (search the Chat manifest for ai-integrations) |
| Stream Moderation review UI or any other non-Chat / non-Video / non-Feeds Stream RN product | Reject bundled scope and route to live docs only if the user wants docs |
Bare /stream-react-native with no args |
List the tracks briefly and wait |
What ships with it
21 files 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.
- ai-integration.md 8.4 KB
- builder.md 42 KB
- credentials.md 22 KB
- migrate.md 14 KB
- references/CHAT-REACT-NATIVE-blueprints.md 27 KB
- references/CHAT-REACT-NATIVE.md 22 KB
- references/design-matching.md 28 KB
- references/DOCS.md 7.1 KB
- references/FEEDS-REACT-NATIVE-blueprints.md 55 KB
- references/FEEDS-REACT-NATIVE.md 39 KB
- references/regions-chat.md 47 KB
- references/regions-feeds.md 8.0 KB
- references/regions-video.md 7.3 KB
- references/sendbird-notes.md 26 KB
- references/sendbird-symbols.tsv 92 KB
- references/SIMULATOR-VERIFICATION.md 27 KB
- references/VIDEO-REACT-NATIVE-blueprints.md 51 KB
- references/VIDEO-REACT-NATIVE.md 44 KB
- RULES.md 29 KB
- sdk.md 20 KB
- sendbird-migration.md 53 KB
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.
- 23d ago Changed · +1 lines · +6 tokens per session 2556f6720456
- 1mo ago First seen · 315 lines · 238 tokens per session scan A f01eb968cd9e
stream-react-native is a skill published in the GitHub repository GetStream/agent-skills (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 244 tokens to every session and 7,882 once invoked, about $0.0010 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
building-ui
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
use-dom
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
app_remix
Create a new Rome app from an App Store source, already installed or identified by a pinned Store version. Copy installed code locally or download and extract a Store bundle without installing the source. Never edit or overwrite an existing source app.
ii-app
Use this skill when you need to initialize or restart local web and mobile app projects through the bundled Rust ii-app CLI instead of calling MCP tools.
release-new-version
Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).