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 instructions/kesha-antonov/react-native-chat/agents-mdgit clone --depth 1 https://github.com/kesha-antonov/react-native-chatWrote 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/instructions/kesha-antonov/react-native-chat/agents-md)<a href="https://agentmods.dev/instructions/kesha-antonov/react-native-chat/agents-md"><img src="https://agentmods.dev/badge/instructions/kesha-antonov/react-native-chat/agents-md.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 | $0.01787 | $0.01787 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade C, and why
react-native-chat AGENTS.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `yarn build` | `rm -rf lib && tsc` - emits `lib/`, which is gitignored and is what gets published. | How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working inside this repository.
If you are instead helping someone use this library in their own app, read
llms.txt - it is a compact integration guide and does not require the checkout.
What this is
@kesha-antonov/react-native-chat is a chat UI component library for React Native and
Web - a maintained continuation of react-native-gifted-chat. It ships as compiled
JavaScript plus type definitions; there is no native code in this package.
Setup
Requires Node >= 20 and Yarn 4 (pinned via packageManager; use yarn, never npm).
yarn install # library
cd example && yarn install && cd .. # example app - a SEPARATE yarn project
The repo is not a Yarn workspace. example/ has its own package.json, its own
yarn.lock, and its own node_modules, and depends on the library via link:... Installing
at the root does not install the example, and vice versa.
Commands
Run these from the repo root:
| Command | What it does |
|---|---|
yarn test |
Jest suite. Must stay green. |
yarn typecheck |
tsc --noEmit over src/. Must stay clean. |
yarn lint |
ESLint over both src/ and example/. Must report 0 errors and 0 warnings. |
yarn lint:fix |
Auto-fix what ESLint can. |
yarn build |
rm -rf lib && tsc - emits lib/, which is gitignored and is what gets published. |
yarn prepublishOnly |
lint + test + build, i.e. the full gate. |
Inside example/: yarn lint and yarn typecheck cover the example app on its own. Note
that the root yarn lint also lints example/, under stricter rules than the example's
own expo lint - so a change that passes cd example && yarn lint can still fail at the root.
Always run the root yarn lint before you finish.
Layout
src/ library source - the only thing published (as compiled lib/)
Chat/ the top-level <Chat> component
MessagesContainer/ list engine (FlatList / FlashList), day header, scroll handling
Bubble/ Message/ a single message row and its bubble
Reactions/ Reply/ emoji reactions, swipe-to-reply
components/ shared leaf components (Icon, TouchableOpacity, markdown, voice…)
hooks/ useTheme, useLabels, useStreamingMessages, …
locales/ i18n.ts built-in UI translations (en, es, fr, de, ru)
Models.ts IMessage, User, QuickReplies, MessageReaction - the public data model
index.ts types.ts public API surface; anything not exported here is internal
__tests__/ Jest tests, colocated with the source they cover
tests/setup.ts global Jest mocks (reanimated, worklets, safe-area, keyboard)
example/ Expo demo app - separate yarn project, consumes the built lib/
docs/ MIGRATION.md, STREAMING.md
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 First seen · 151 lines · 1,787 tokens per session scan C b9581d5027b6
react-native-chat AGENTS.md is an instructions file published in the GitHub repository kesha-antonov/react-native-chat (47 stars, last pushed 6d ago), licensed MIT. It adds 1,787 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
sceneview copilot-instructions.md
Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
sceneview CLAUDE.md
Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
cc-pocket AGENTS.md
Instructions for heypandax/cc-pocket, covering agents.md — cc-pocket, ⚠️ 本机 daemon 操作铁律(最重要,先读这一段), 改完 daemon 代码要更新本机 daemon —— 只用这一条命令, 绝对不要做(每一条都会制造第二个 daemon → 立刻不可用) and 必须知道的两个反直觉事实(本机环境).
debroid AGENTS.md
Instructions for PatilShreyas/debroid, covering ai agent contributor guide 🤖, 🎯 intention & motivation, 🏗️ architecture & layers, 1. the core layer (jdi & adb orchestration) and 2. the cli layer (daemon & client).
PdfKmp CLAUDE.md
Instructions for ConaMobileDev/PdfKmp, covering claude.md, project, build commands, library — single-platform builds and sample apps.
DSH-Mobile AGENTS.md
Instructions for SimonMedy/DSH-Mobile, covering agents.md — dsh mobile engineering contract, product boundary, security invariants, dependency policy and architecture.