agentmods.dev

agentao: Instructions file for Claude Code

CLAUDE.md

agentao CLAUDE.md is an instructions file for Claude Code from jin-bo/agentao. It costs 11,259 tokens per session, scanned C, original, MIT.

A repository guide for Agentao, a Python tool for running AI-agent workflows from an interactive or command-line interface. It documents package management, commands, optional features, and the main ways to run the tool.

In plain words
What is it for?
Setting up Agentao, running prompts interactively or automatically, starting its ACP server, and working with its optional command-line features.
Why use it?
It prevents using the wrong dependency or startup commands. It also clarifies which optional components are needed for different tasks.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is jin-bo/agentao's own configuration. It tells Claude Code how to work on agentao itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentao configures →

not rated 310repo changed 8d ago C scan 11,259 tokens original MIT
View source ↗ jin-bo/agentao agentao.cn
Reuse

Borrowing it

Nothing to install: this file belongs to jin-bo/agentao. 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/jin-bo/agentao/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jin-bo/agentao

Made for: Claude Code.

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.

agentmods badge for agentao CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jin-bo/agentao/claude-md/github.svg)](https://agentmods.dev/instructions/jin-bo/agentao/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jin-bo/agentao/claude-md"><img src="https://agentmods.dev/badge/instructions/jin-bo/agentao/claude-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.

agentmods 80×15 button for agentao CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jin-bo/agentao/claude-md"><img src="https://agentmods.dev/badge/instructions/jin-bo/agentao/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,259 This file is loaded in full into every session.
When invoked 11,259 The same file — it is already loaded in full.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.11259 $0.11259
Opus 5.5 $0.04504 $0.04504
Sonnet 5.5 $0.02252 $0.02252
Haiku 4.5 $0.01126 $0.01126

Measured 8d ago against content hash 40ae9af5291b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

agentao CLAUDE.md scanned grade C with 2 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 8d 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.

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

The engine does **no file I/O**. `embedding/permission_loader.py::load_permission_rules()` reads `(rules, sources)` and passes them in. The default presets allow common docs domains and deny SSRF targets (`localhost`, `1

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **For batch commands, use `capabilities/process.py::run_captured()`, not `subprocess.run`** (PRs #73–#75).
CLAUDE.md · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 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.

This file keeps the rules and invariants that are easy to break. The reasons for them are in the linked design docs, in module docstrings, and in the cited PRs and issues. Read those before you change a rule.

Package Management

Always use uv for package management. Do not use pip:

uv sync                    # Install dependencies
uv add package-name        # Add a new dependency
uv run python script.py    # Run Python scripts
uv run agentao             # Run the CLI
  • Core dependencies are in [project.dependencies]. UI, fetch and tokenization dependencies are opt-in extras. Both wire SDKs (openai, anthropic) are core, imported lazily.
  • A bare pip install agentao installs the library only. pip install 'agentao[cli]' is the smallest interactive CLI.
  • The [pdf] / [excel] / [image] / [crypto] / [google] extras were removed (docs/design/optimization-opportunities-review.md T1.1).

Running

./run.sh                              # Quick start (interactive)
uv run agentao                        # Interactive CLI
uv run python -m agentao              # Same, via module entrypoint
uv run agentao run --prompt "..."     # Non-interactive automation (M0)
uv run agentao --acp --stdio          # ACP server (Issue 12)

agentao run is the canonical non-interactive surface. Its exit codes are 0 ok, 1 runtime, 2 invalid usage, 3 permission/interaction, 4 max iterations, 130 interrupted. See agentao/cli/run.py and docs/reference/configuration.md. agentao -p "..." is a thin shim over agentao run.

Testing

uv run python -m pytest tests/       # Default suite
uv run python -m pytest tests/ -n logical  # Parallel (pytest-xdist): CI on Windows, and on Linux for PRs (pushes to main stay serial)
uv run python -m pytest -m slow      # Clean-install smoke tests (needs `uv build` first)
uv run ruff check .                  # Lint gate — required CI check
(cd developer-guide && npm ci && npm run docs:build) && python3 scripts/check_guide_anchors.py developer-guide  # Guide pages + anchors — CI job

Read the full file on GitHub · 494 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.

  1. 8d ago Changed · +2 lines · +206 tokens per session 40ae9af5291b
  2. 9d ago Changed · +7 lines · +426 tokens per session 7fc936a7bd94
  3. 19d ago Changed · +2 lines · +145 tokens per session ee2c1cd3270a
  4. 23d ago Changed · +14 tokens per session 5de25878053e
  5. 26d ago Changed · +1 lines · +123 tokens per session 825fe2130aeb
  6. 27d ago Changed · +14 lines · -8,979 tokens per session cc6f9c61a16d
  7. 28d ago Changed · +76 tokens per session dfd1a696982c
  8. 29d ago Changed · +1 lines · +35 tokens per session 8fff1c378396
  9. 1mo ago Changed · +95 tokens per session c2ff504a11b4
  10. 1mo ago First seen · 467 lines · 19,118 tokens per session scan C 9058770d0560

Subscribe to this mod's changes

agentao CLAUDE.md is an instructions file published in the GitHub repository jin-bo/agentao (310 stars, last pushed 4d ago), licensed MIT. It adds 11,259 tokens to every session, about $0.0450 per session on Opus 5.5. A static security scan graded it C with 2 findings (cloud metadata endpoint, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsLLMacpagent-frameworkai-agentclilocal-first
Related

agentao CLAUDE.md compared with instructions from other repositories

agentao CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentao CLAUDE.mdjin-bo/agentaoInstructions file3104d agoMITC11,259Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode