agent-state: Instructions file for Codex

AGENTS.md

agent-state AGENTS.md is an instructions file for Codex, OpenCode from tianhuil/agent-state. It costs 208 tokens per session, scanned A, original, MIT.

A set of project instructions for Python repositories, covering package management, code style, type annotations, documentation, error handling, and validation.

In plain words
What is it for?
Use it when working on the agent-state Python project, especially when installing dependencies with uv, writing typed code, documenting functions and classes, and running ruff and pyright.
Why use it?
It gives a coding agent consistent rules for making and checking changes in the repository. It also explains which tools to use to find style and type problems.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is tianhuil/agent-state's own configuration. It tells Codex and OpenCode how to work on agent-state 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 agent-state configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tianhuil/agent-state. 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/tianhuil/agent-state/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tianhuil/agent-state

Made for: Codex, OpenCode.

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 agent-state AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tianhuil/agent-state/agents-md/github.svg)](https://agentmods.dev/instructions/tianhuil/agent-state/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tianhuil/agent-state/agents-md"><img src="https://agentmods.dev/badge/instructions/tianhuil/agent-state/agents-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 agent-state AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tianhuil/agent-state/agents-md"><img src="https://agentmods.dev/badge/instructions/tianhuil/agent-state/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 This file is loaded in full into every session.
When invoked 208 The same file — it is already loaded in full.
Security scan A 0 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 $0.00208 $0.00208
Opus 5.5 $0.00083 $0.00083
Sonnet 5.5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 2mo ago against content hash e5e39ea26986, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-state AGENTS.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 2mo 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.

AGENTS.md · 21 lines

What it actually says

Rules for python repos

General

  • Use uv for package manager.

Coding Style

  • Prefer to write functional code. Prefer list comprehensions for map, flatmap, and filter: [func(x) for x in xs if condition(x)].
  • Prefer to not mutate variables, even though Python allows mutation (pretend variables are all using typescript const not let).
  • Explicitly type where practicable using mypy. Look at the libraries and import and use those types; do not make up types.
  • Always avoid using type Any type.
  • Add docstring to every class and function.
  • Place try/except only at the root calling function. Do not place try/except in each intermediate or leaf function.

Validation

Whenever you make a change, run ruff and pyright to confirm tests pass. Use git diff and review code changes for following the rules under "Coding Style" section.

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. 2mo ago First seen · 21 lines · 208 tokens per session scan A e5e39ea26986

Subscribe to this mod's changes

agent-state AGENTS.md is an instructions file published in the GitHub repository tianhuil/agent-state (0 stars, last pushed 11mo ago), licensed MIT. It adds 208 tokens to every session, about $0.0008 per session on Opus 5.5. 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.

Related

agent-state AGENTS.md compared with instructions from other repositories

agent-state AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-state AGENTS.mdtianhuil/agent-stateInstructions file011mo agoMITA208Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot