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/unicomai/wanwu-workflow/claude-mdgit clone --depth 1 https://github.com/UnicomAI/wanwu-workflowWrote 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/unicomai/wanwu-workflow/claude-md)<a href="https://agentmods.dev/instructions/unicomai/wanwu-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/unicomai/wanwu-workflow/claude-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 | $0.01417 | $0.01417 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
wanwu-workflow CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Coze Studio is an all-in-one AI agent development platform with both frontend (React + TypeScript) and backend (Go) components. The project uses a sophisticated monorepo architecture managed by Rush.js with 135+ frontend packages organized in a hierarchical dependency system.
Development Commands
Environment Setup
# Clone and setup
git clone https://github.com/coze-dev/coze-studio.git
cd coze-studio
# Install frontend dependencies
rush update
# For Docker-based development
cd docker
cp .env.example .env
# Configure model settings in backend/conf/model/
docker compose up -d
# Access at http://localhost:8888
Development Workflow
# Start middleware services (MySQL, Redis, Elasticsearch, etc.)
make middleware
# Start Go backend in development mode
make server
# Start frontend development server
cd frontend/apps/coze-studio
npm run dev
# Full development environment
make debug
Build Commands
# Build frontend only
make fe
# Build Go server
make build_server
# Build everything with Docker
make web
# Rush monorepo commands
rush build # Build all packages
rush rebuild -o @coze-studio/app # Build specific package
rush test # Run all tests
rush lint # Lint all packages
Testing
# Run tests (Vitest-based)
rush test
npm run test # In specific package
npm run test:cov # With coverage
# Backend tests
cd backend && go test ./...
Architecture Overview
Frontend Architecture
- Monorepo: Rush.js with 135+ packages across 4 dependency levels
- Build System: Rsbuild (Rspack-based) for fast builds
- UI Framework: React 18 + TypeScript + Semi Design + Tailwind CSS
- State Management: Zustand for global state
- Package Organization:
arch/: Core infrastructure (level-1)common/: Shared components and utilities (level-2)agent-ide/,workflow/,studio/: Feature domains (level-3)apps/coze-studio: Main application (level-4)
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.
- 4d ago First seen · 196 lines · 1,417 tokens per session scan A 8afec935d499
wanwu-workflow CLAUDE.md is an instructions file published in the GitHub repository UnicomAI/wanwu-workflow (43 stars, last pushed 28d ago), licensed Apache-2.0. It adds 1,417 tokens to every session, about $0.0071 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 instructions, from other repositories
agent-nexus AGENTS.md
Instructions for canoo/agent-nexus: This repository is managed by the NEXUS Framework (Network of EXperts, Unified in Strategy). For detailed operational instructions, agent personas, and workflow logic, please refer to the core definition file.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
rome CLAUDE.md
Claude Code instructions for rome-os/rome, covering rome, playbook and traps.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).