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/jin-bo/agentao/claude-mdgit clone --depth 1 https://github.com/jin-bo/agentaoWrote 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/jin-bo/agentao/claude-md)<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="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 | $0.09783 | $0.09783 |
| Opus 5 | $0.04892 | $0.04892 |
| Sonnet 5 | $0.01957 | $0.01957 |
| Haiku 4.5 | $0.00978 | $0.00978 |
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 today.
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.
**Confirmation / permissions**: `PermissionEngine` evaluates rules from `.agentao/permissions.json` (project) + `<home>/.agentao/permissions.json` (user). Precedence in `runtime/tool_planning.py::_decide` is three-tier, Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Don't call `subprocess.run` for batch commands — use `agentao/capabilities/process.py::run_captured()`.** A bare `subprocess.run(timeout=)` only kills the direct child on timeout, so a grandchild holding the captured How it starts
The opening of the file, as written. The whole thing — 374 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.
Package Management
Always use uv for package management, not 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 deps live in [project.dependencies]; the heavyweight UI / fetch / tokenization deps are opt-in extras. A bare pip install agentao gets a library-only install; pip install 'agentao[cli]' is the smallest interactive CLI. (The [pdf] / [excel] / [image] / [crypto] / [google] extras were removed as dead weight — zero in-tree consumers; see 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. Exit codes: 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. The legacy agentao -p "..." is now a thin shim over agentao run.
Testing
uv run python -m pytest tests/ # Default suite
uv run python -m pytest -m slow # Clean-install smoke tests
uv run ruff check . # Lint gate — required CI check
The slow marker is excluded by default (pyproject.toml :: tool.pytest.ini_options.addopts = "--tb=short -m 'not slow'").
ruff check . is a required CI check, so a green pytest run is not enough before pushing. The gate is deliberately narrow — defect rules only (E9, F401, F402, F405, F811, F821), no style — and the rules and scope both live in pyproject.toml, so the command above is character-for-character what CI runs. Two non-obvious parts: F405 is selected because F821 is silently inert in the 8 star-import modules without it, and F401 is exempted for agentao/ because a name re-exported for downstream embedders is indistinguishable from dead code to a single-file linter. Suppress with a reason (# noqa: F401 — pytest fixture injection), never bare. See docs/design/lint-gate.md.
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.
- today Changed · +188 tokens per session d1381560fb80
- 4d ago First seen · 374 lines · 9,595 tokens per session scan C 6355d5c23afa
agentao CLAUDE.md is an instructions file published in the GitHub repository jin-bo/agentao (95 stars, last pushed 3d ago), licensed MIT. It adds 9,783 tokens to every session, about $0.0489 per session on Opus 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.
Other instructions, from other repositories
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).
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.
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.