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/zero565656/mini-openclaw/claude-mdgit clone --depth 1 https://github.com/zero565656/mini-openclawWhat 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 | $0.02156 | $0.02156 |
| Opus 5 | $0.01078 | $0.01078 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
mini-openclaw 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 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.
How it starts
The opening of the file, as written. The whole thing — 242 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
Mini-OpenClaw is a file-first AI agent system with a React frontend and FastAPI/LangGraph backend. It combines conversational AI with transparent file-based memory, skills plugins, and RAG knowledge retrieval.
Core Philosophy
- File-first Memory: All persistent state (sessions, memory, skills) is stored as files, not databases
- Skills as Plugins: Custom tools defined in
backend/skills/*/SKILL.mdfiles - Transparent Thinking: Agent tool calls and reasoning are displayed to the user in real-time
- No Cloud Lock-in: Uses local LLM (DeepSeek/Claude/OpenAI) and on-disk storage
Development Commands
Environment Setup
# Activate conda environment (required for backend)
conda activate langgraph
# Install frontend dependencies
cd frontend
npm install
Running the Project
Important: On Windows, use the following ports due to Hyper-V port reservation issues (see DEV_NOTES.md):
- Backend: 9000 (not 8000/8002/8888 which are reserved)
- Frontend: 5173
Terminal 1 - Backend (run from project root):
conda activate langgraph
python -m uvicorn backend.app:app --reload --port 9000
Terminal 2 - Frontend (run from frontend directory):
cd frontend
npm run dev
Frontend Commands
npm run dev # Start dev server
npm run build # Production build
npm run lint # ESLint
npm run test # Run vitest tests
npm run test:watch # Watch mode for tests
Backend Testing
# Access Swagger UI for API documentation
# http://localhost:9000/docs
Architecture
Frontend (React + Vite + shadcn/ui)
frontend/
├── src/
│ ├── pages/Index.tsx # Main layout (3-panel: Sidebar | Chat | Inspector)
│ ├── components/
│ │ ├── ChatStage.tsx # Chat interface with streaming + thinking chain
│ │ ├── AppSidebar.tsx # Sessions list + System prompt view
│ │ └── InspectorPanel.tsx # File editor for memory/skills
│ ├── lib/store.tsx # React Context for global state
│ └── api.ts # API client (streaming fetch, sessions, files)
└── vite.config.ts # IMPORTANT: host: "localhost" (not "::") for Windows
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 · 242 lines · 2,156 tokens per session scan A 14c96fa175e8
mini-openclaw CLAUDE.md is an instructions file published in the GitHub repository zero565656/mini-openclaw (2 stars, last pushed 6mo ago), licensed MIT. It adds 2,156 tokens to every session, about $0.0108 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.