What is autocontext AGENTS.md?

A guide for coding agents working in the autocontext repository, covering which project area to use, where to run Python and TypeScript commands, setup steps, and checks for keeping implementations consistent.

Use it when setting up or modifying the Python toolkit, TypeScript toolkit, terminal interface, or agent integration documentation in that repository.

It prevents commands from being run in the wrong directory and clarifies when changes to public commands, settings, or workflows require matching documentation updates.

How greyhaven-ai/autocontext configures Codex and OpenCode

About the project

autocontext is a self-improving harness for AI agents that runs a goal through evaluation, preserves useful lessons, and records artifacts for later runs. Developers use it to help agents and future versions of those agents perform better on recurring tasks. The catalogue add-ons support its agent-improvement workflow.

greyhaven-ai/autocontext · 1,321 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to greyhaven-ai/autocontext. 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/greyhaven-ai/autocontext/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/greyhaven-ai/autocontext

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/greyhaven-ai/autocontext/agents-md/github.svg)](https://agentmods.dev/instructions/greyhaven-ai/autocontext/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/greyhaven-ai/autocontext/agents-md"><img src="https://agentmods.dev/badge/instructions/greyhaven-ai/autocontext/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/greyhaven-ai/autocontext/agents-md"><img src="https://agentmods.dev/badge/instructions/greyhaven-ai/autocontext/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 536 This file is loaded in full into every session.

When invoked 536 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.

Model	Per session	Once invoked
Fable 5.1	$0.00536	$0.00536
Opus 5.5	$0.00214	$0.00214
Sonnet 5.5	$0.00107	$0.00107
Haiku 4.5	$0.00054	$0.00054

Measured 2mo ago against content hash 77ecb3672400, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autocontext 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

Use this file as the first pointer for coding agents and automation that need to work in or against this repo.

Pick The Right Surface

Full autocontext control plane: autocontext/
Node/TypeScript toolkit and CLI: ts/
Interactive terminal UI: ts/src/tui/
External agent usage guide: autocontext/docs/agent-integration.md

Working Directories

Run Python commands from autocontext/.
Run Node/TypeScript commands from ts/.
Run TUI-related commands from ts/.

Most repo-level commands in the READMEs assume one of those package directories as the current working directory.

Setup

Python:

cd autocontext
uv venv
source .venv/bin/activate
uv sync --group dev

TypeScript:

cd ts
npm install

Parity-Last Changes

Implement one runtime first unless cross-runtime parity is user-visible in the same release. If parity is deferred, say where and why in the PR.

Common Checks

Python:

cd autocontext
uv run ruff check src tests
uv run mypy src
uv run pytest

TypeScript:

cd ts
npm run lint
npm test

Public Docs To Keep In Sync

If you change public commands, environment variables, package names, or agent-facing workflows, update the relevant docs in the same change:

README.md
docs/README.md
autocontext/README.md
ts/README.md
examples/README.md
autocontext/docs/agent-integration.md
CONTRIBUTING.md
CHANGELOG.md

Key References

Repo overview: README.md
Docs overview: docs/README.md
Contributor workflow: CONTRIBUTING.md
Python package guide: autocontext/README.md
TypeScript package guide: ts/README.md
Copy-paste examples: examples/README.md
External agent guide: autocontext/docs/agent-integration.md

Intentional Deletions

Before restoring deleted modules to make CI green, check whether autocontext/src/ still imports them.
If only tests are failing, prefer rewriting or deleting the tests instead of restoring removed modules.
Treat importable module paths as compatibility surfaces until callers are rewired or the removal is explicitly accepted as breaking.

Read the full file on GitHub · 89 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.

2mo ago First seen · 89 lines · 536 tokens per session scan A 77ecb3672400

Subscribe to this mod's changes

autocontext AGENTS.md is an instructions file published in the GitHub repository greyhaven-ai/autocontext (1,321 stars, last pushed yesterday), licensed Apache-2.0. It adds 536 tokens to every session, about $0.0021 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 2026-08-30.

agents ai autoresearch llms ml openclaw

autocontext AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autocontext AGENTS.mdgreyhaven-ai/autocontext	Instructions file	1.3k	yesterday	Apache-2.0	A	536	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

autocontext: Instructions file for Codex