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/getstream/stream-chat-react/worktreesnpx skills add GetStream/stream-chat-react --skill worktreesgit clone --depth 1 https://github.com/GetStream/stream-chat-reactWhat 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 | $0.00055 | $0.00784 |
| Opus 5 | $0.00028 | $0.00392 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
worktrees 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 95 lines · 55 tokens per session scan A c95995b91200
worktrees is a skill published in the GitHub repository GetStream/stream-chat-react (841 stars, last pushed 3d ago), with no licence file. It adds 55 tokens to every session and 784 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 2026-08-30.
Other skills, from other repositories
accessibility
Maintain VoiceOver/TalkBack-focused accessibility in stream-chat-react-native. Use when changing interactive components, gestures, modals, lists, media controls, notifications, focus behavior, or live announcements.
perf-benchmarking
Measure React Native performance on-device for stream-chat-react-native — Hermes CPU profiles, deterministic call/listener counting, component render profiling, and memory/jank capture. Use when asked to benchmark a change, prove or disprove a perf claim, compare before/after, find what re-renders or what's heavy on…
rtl
Audit and maintain RTL (right-to-left) layout compatibility in stream-chat-react-native. Use when changing styles, positioning, flex layouts, swipe gestures, animated transforms, icons, text alignment, or anything that has a horizontal/directional axis.
UI Designer
React + TypeScript + Tailwind CSS chat interface specialist for this project's streaming chat UI.
developer
Feature development for this repo — XP, DDD, BDD, TDD, Glossary naming, Apple HIG minimal UX, living docs sync (C4 / Glossary / User Story Map), and mandatory commit/PR standards (why body + References from official docs and research). Use when implementing features, writing tests, committing, opening PRs, UI work, or…
spring-ai
Spring AI 2.0 Development Guide. Covers ChatClient API, Structured Output, RAG, Tool Calling, Embeddings, Vector Store, MCP Integration, Clean Architecture Integration.