composio: Instructions file for Codex

AGENTS.md

composio AGENTS.md is an instructions file for Codex, OpenCode from ComposioHQ/composio. It costs 1,464 tokens per session, scanned A, original, MIT.

Repository-wide instructions for AI coding agents working in Composio's monorepo, a single repository containing multiple related SDKs and documentation.

In plain words
What is it for?
Use it before making changes in the repository, especially when deciding where code belongs or which local skill to follow.
Why use it?
It explains the repository layout, safe editing rules, branch expectations, generated files, and how to choose other instructions for a task.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is ComposioHQ/composio's own configuration. It tells Codex and OpenCode how to work on composio 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 composio configures →

About the project

Composio is a software toolkit that gives AI agents access to authenticated tools for interacting with apps and services. Developers use its SDKs, command-line interface, sessions, and sandbox to build agents that can carry out actions. The catalogue add-ons support workflows for using Composio with coding agents.

ComposioHQ/composio · 30,947 stars · on GitHub · docs.composio.dev

Reuse

Borrowing it

Nothing to install: this file belongs to ComposioHQ/composio. 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/ComposioHQ/composio/next/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ComposioHQ/composio

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 composio AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/composiohq/composio/agents-md"><img src="https://agentmods.dev/badge/instructions/composiohq/composio/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,464 This file is loaded in full into every session.
When invoked 1,464 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 $0.01464 $0.01464
Opus 5.5 $0.00586 $0.00586
Sonnet 5.5 $0.00293 $0.00293
Haiku 4.5 $0.00146 $0.00146

Measured 7d ago against content hash 33bf2acf85bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

composio 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 7d 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Repository guidance for Codex, Claude Code, Cursor, pi.dev, and other AI coding agents.

Scope

This is the Composio SDK v3 monorepo. Most product code lives in ts/ and python/; docs live in docs/. Branch new work from next and target PRs at next unless the user says otherwise.

First Steps

  1. Read the nearest nested AGENTS.md before editing a subtree.
  2. Preserve unrelated dirty work. Do not revert, delete, or reformat files outside the requested scope.
  3. Treat .agents/skills as the canonical local skill tree. .claude/skills is a compatibility symlink and must not be edited as a separate copy.
  4. Do not edit generated SDK surfaces or vendor trees — see Generated And Vendored Paths.
  5. Verify every command you write against the current package.json, Makefile, noxfile.py, or workflow file.

Contribution Policy

Follow the Contribution Policy in CONTRIBUTING.md. When helping an author prepare a PR:

  • Composio team members and designated maintainers can open PRs directly. External contributors need an existing, open issue; if none is linked, tell the author to open one first. For large external changes, get maintainer agreement on the approach before implementation.
  • @jkomyno is the designated PR reviewer. Involve the relevant owner when the change needs their expertise.
  • Keep the change focused on meaningful improvements to the SDKs, CLI, or docs. Don't produce cosmetic, speculative, or drive-by edits.
  • The author is responsible for every line. Keep diffs small enough to read, report the checks you actually ran, and tell the author to review the full diff before submitting.
  • Follow the third-party links policy. Authoritative technical references needed to use or contribute to Composio are allowed; other third-party links and promotional content must fit the listed exceptions. Route partnership requests to https://composio.dev/contact.

Read the full file on GitHub · 120 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. 7d ago Changed · +3 lines · +56 tokens per session 33bf2acf85bd
  2. 1mo ago Changed · -1 lines · -33 tokens per session 836b8f54b4af
  3. 1mo ago Changed · +10 lines · +251 tokens per session a70009c69cd8
  4. 1mo ago Changed · +2 lines · +47 tokens per session 72aeeb943023
  5. 2mo ago First seen · 106 lines · 1,143 tokens per session scan A ed82ccaff5a3

Subscribe to this mod's changes

composio AGENTS.md is an instructions file published in the GitHub repository ComposioHQ/composio (30,947 stars, last pushed yesterday), licensed MIT. It adds 1,464 tokens to every session, about $0.0059 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.

Related

composio AGENTS.md compared with instructions from other repositories

composio AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
composio AGENTS.mdComposioHQ/composioInstructions file31kyesterdayMITA1,464Codex, 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 file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode