What is Clawy AGENTS.md?

Project-specific development instructions for Clawy, a cross-platform desktop app built with Tauri, React, Vite, TypeScript, and Rust. It documents commands, setup details, and less obvious environment requirements.

Use it when installing dependencies, running development servers, checking code, running tests, or building Clawy for the web or desktop.

It gives coding agents the repository context and workflow they need to work consistently, including the required package-manager version and headless Linux caveats.

How edwardZhang/Clawy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to edwardZhang/Clawy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/edwardZhang/Clawy/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/edwardZhang/Clawy

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/edwardzhang/clawy/agents-md/github.svg)](https://agentmods.dev/instructions/edwardzhang/clawy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/edwardzhang/clawy/agents-md"><img src="https://agentmods.dev/badge/instructions/edwardzhang/clawy/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/edwardzhang/clawy/agents-md"><img src="https://agentmods.dev/badge/instructions/edwardzhang/clawy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,169 This file is loaded in full into every session.

When invoked 1,169 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01169	$0.01169
Opus 5.5	$0.00468	$0.00468
Sonnet 5.5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured 2mo ago against content hash 45c2863ed79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Clawy AGENTS.md 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 2mo 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Overview

Clawy is a cross-platform Tauri desktop app (React 19 + Vite + TypeScript, Rust core) providing a GUI for the OpenClaw AI agent runtime. It uses pnpm as its package manager (pinned version in package.json's packageManager field).

Quick reference

Standard dev commands are in package.json scripts and README.md. Key ones:

Task	Command
Install deps + download uv	`pnpm run init`
Dev server (Vite + Tauri)	`pnpm dev`
Lint (ESLint, auto-fix)	`pnpm run lint`
Type check	`pnpm run typecheck`
Unit tests (Vitest)	`pnpm test`
Build frontend only	`pnpm run build:vite`
Build desktop app	`pnpm run build:tauri`

Non-obvious caveats

pnpm version: The exact pnpm version is pinned via packageManager in package.json. Use corepack enable && corepack prepare to activate the correct version before installing.
Tauri on headless Linux: The dbus errors (Failed to connect to the bus) are expected and harmless in a headless/cloud environment. The app still runs fine with $DISPLAY set (e.g., :1 via Xvfb/VNC).
pnpm run lint race condition: If pnpm run uv:download was recently run, ESLint may fail with ENOENT: no such file or directory, scandir '/workspace/temp_uv_extract' because the temp directory was created and removed during download. Simply re-run lint after the download script finishes.
Build scripts warning: pnpm install may warn about ignored build scripts for @discordjs/opus and koffi. These are optional messaging-channel dependencies and the warnings are safe to ignore.
pnpm run init: This is a convenience script that runs pnpm install followed by pnpm run uv:download. Either run pnpm run init or run the two steps separately.
Gateway startup: When running pnpm dev, the OpenClaw Gateway process starts automatically on port 18789. It takes ~10-30 seconds to become ready. Gateway readiness is not required for UI development—the app functions without it (shows "connecting" state).
No database: The app uses JSON files under the app data directory plus OS-native secure storage. No database setup is needed.
AI Provider keys: Actual AI chat requires at least one provider API key configured via Settings > AI Providers. The app is fully navigable and testable without keys.
Token usage history implementation: Dashboard token usage history is not parsed from console logs. It reads OpenClaw session transcript .jsonl files under the local OpenClaw config directory, extracts assistant messages with message.usage, and aggregates fields such as input/output/cache/total tokens and cost from those structured records.

Read the full file on GitHub · 64 lines

Changes

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.

2mo ago First seen · 64 lines · 1,169 tokens per session scan A 45c2863ed79a

Subscribe to this mod's changes

Clawy AGENTS.md is an instructions file published in the GitHub repository edwardZhang/Clawy (2 stars, last pushed 7mo ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0047 per session on Opus 5.5. 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.

ai-agents anthropic automation cha-t chat codex

Clawy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Clawy AGENTS.mdedwardZhang/Clawy	Instructions file	2	7mo ago	MIT	A	1,169	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Clawy: Instructions file for Codex