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/akarachen/aghub/claude-mdgit clone --depth 1 https://github.com/AkaraChen/aghubWrote 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/akarachen/aghub/claude-md)<a href="https://agentmods.dev/instructions/akarachen/aghub/claude-md"><img src="https://agentmods.dev/badge/instructions/akarachen/aghub/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 | $0.05671 | $0.05671 |
| Opus 5 | $0.02835 | $0.02835 |
| Sonnet 5 | $0.01134 | $0.01134 |
| Haiku 4.5 | $0.00567 | $0.00567 |
Grade A, and why
aghub 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 5d 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 — 128 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
aghub is a CLI tool (aghub-cli) for managing AI coding agent configurations. It supports 22 agents (Claude, OpenCode, Cursor, Windsurf, Copilot, RooCode, Cline, Gemini, Codex, Zed, Warp, and more), handling MCP servers and skills through a unified interface. Full agent list: crates/core/src/models.rs or aghub-cli --help.
Common Commands
Use just for task running:
# Build
just dev # Debug build
just build # Release build
# Test
just test # Run all tests
just integration-test # Run integration tests only
just test-with-validation # Tests requiring real CLI tools installed (claude, opencode, etc.)
# Lint/Format
just lint # Run clippy with warnings as errors
just fmt # Format code
# Run
just start -- --help # Run with cargo
just start -- -a claude get skills # List skills
just start -- -a claude get mcps # List MCP servers
just install # Release build → ~/.cargo/bin/
Run a single test: cargo test --package aghub-core test_name -- --exact
Architecture
Workspace Structure
crates/core(aghub-core): Core library with models, config management, and agent adapterscrates/cli(aghub): CLI binary (aghub-cli) with clap-based commandscrates/skills-sh: HTTP API client for skills.sh registry (SKILLS_API_URLenv var overrides base URL)crates/skills-ref(skills-ref): Parses SKILL.md files, validatesSkillProperties, generates XML prompt blocks viato_prompt()crates/skill(skill): Extends skills-ref with.skillzip format;parse()auto-detects directory/zip/SKILL.md. Called bymanager.add_skill_from_path()crates/prompt(aghub-prompt): Local prompt-library storage —Promptmodel plus a JSON-filePromptStore(CRUD overprompts.jsonin the app data dir) and{{variable}}extractioncrates/api: Rocket-based HTTP API server exposing agent config operations over HTTP
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.
- 5d ago First seen · 128 lines · 5,671 tokens per session scan A 2f3839d2c9f5
aghub CLAUDE.md is an instructions file published in the GitHub repository AkaraChen/aghub (264 stars, last pushed 2d ago), licensed MIT. It adds 5,671 tokens to every session, about $0.0284 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
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
gandalf CLAUDE.md
Instructions for sebacaro/gandalf, covering gandalf — cli para spec driven development, comandos, activar entorno, ejecutar directamente and o con gandalf global (después de install.sh).