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/lichas/maxclaw/claude-mdgit clone --depth 1 https://github.com/Lichas/maxclawWhat 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 | $0.01520 | $0.01520 |
| Opus 5 | $0.00760 | $0.00760 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
maxclaw 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 2d 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 — 160 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
maxclaw is an ultra-lightweight personal AI assistant framework written in Go (~3,500 lines of core code). It provides core agent functionality including tool use, multi-channel chat integrations, and scheduled tasks.
- Language: Go 1.24+
- Module:
github.com/Lichas/maxclaw - Entry point:
cmd/maxclaw/main.go - Binary name:
maxclaw
Operating Rules (Must Follow)
- Do not ask the user to verify. You are responsible for running tests, validating behavior, and reporting results.
- Always verify changes: run relevant tests or smoke checks, and report what passed/failed.
- After successfully completing a request with repository changes, run
make buildand then create agit commitfor that request. - If you fix a bug, append a concise entry to
BUGFIX.md(what broke, root cause, fix, verification). - If a request changes repository files, append a concise entry to
CHANGELOG.mdunder## [Unreleased](what changed, key files, verification command). - When adding features, update the docs (README / architecture) and validate the path end-to-end.
- Assume ownership of outcomes: if something could be flaky, add logging/guards and document the caveats.
- For runtime incidents, follow
MAINTENANCE.mdfirst (process/port/proxy/log order) before ad-hoc debugging.
Development Commands
Build & Run
make build # Build to build/maxclaw
make install # Install to GOPATH/bin
make run # Build and run
make dev # Hot reload (requires air)
Testing
make test # Run all tests (go test -v ./...)
make coverage # Generate coverage report
# OR
go test ./... # Direct go test
go test -v ./... # Verbose output
go test -cover ./... # With coverage
Code Quality
make fmt # Format code (go fmt ./...)
make vet # Run go vet
make lint # Run fmt and vet
make mod # Tidy and verify modules
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.
- 2d ago First seen · 160 lines · 1,520 tokens per session scan A d68118958fde
maxclaw CLAUDE.md is an instructions file published in the GitHub repository Lichas/maxclaw (231 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,520 tokens to every session, about $0.0076 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
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
clawmetry AGENTS.md
Instructions for vivekchand/clawmetry, covering agents.md — for ai coding agents, quick context, where new code goes (open-core split), the rules that bite and common tasks.
open-xiaoai-bridge AGENTS.md
Instructions for coderzc/open-xiaoai-bridge, covering agents.md, 系统架构, 项目结构, 核心组件 and mainapp (core/app.py).
agent-lsp CLAUDE.md
Instructions for blackwell-systems/agent-lsp, a project described as: MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.
agenticros AGENTS.md
Instructions for agenticros/agenticros, covering agenticros, what this is, important: controlling the robot from codex, architecture and key source files.
OpenPersona AGENTS.md
Instructions for acnlabs/OpenPersona, covering agents.md, project overview, setup, project structure and architecture rules.