crewAI: Instructions file for Codex

AGENTS.md

crewAI AGENTS.md is an instructions file for Codex, OpenCode from crewAIInc/crewAI. It costs 452 tokens per session, scanned A, original, MIT.

A set of contribution instructions for CrewAI, a Python framework for building software agents. It covers coding practices, tests, documentation, and safe handling of message content.

In plain words
What is it for?
Use it when changing CrewAI code or documentation, writing behavior-focused unit tests, preserving its existing structure, or processing text and multimodal message content.
Why use it?
It gives coding agents project-specific rules, reducing inconsistent changes and mistakes when working in the CrewAI codebase.

Instructions file for CodexOpenCode

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

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

About the project

CrewAI is an open-source Python framework for building workflows in which multiple AI agents collaborate or follow controlled, event-driven processes. Developers use its role-based Crews and precise Flows to automate tasks involving language models and connected systems.

crewAIInc/crewAI · 60,549 stars · on GitHub · crewai.com

Reuse

Borrowing it

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

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 crewAI AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crewaiinc/crewai/agents-md"><img src="https://agentmods.dev/badge/instructions/crewaiinc/crewai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 452 This file is loaded in full into every session.
When invoked 452 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 $0.00452 $0.00452
Opus 5.5 $0.00181 $0.00181
Sonnet 5.5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2mo ago against content hash 03a3efb0ebb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crewAI 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 · 46 lines

What it actually says

Agent Instructions for CrewAI OSS

CrewAI is a Python based framework for building AI agents and agentic systems. Follow these guidelines when contributing:

Key Guidelines

  1. Follow Python best practices and idiomatic patterns.
  2. Maintain existing code structure and organization.
  3. Write unit tests for new functionality focusing on behaivor and not implementation.
  4. Document public APIs and complex logic.
  5. Suggest changes to the docs/ folder when appropriate
  6. Follow software principles such as DRY and YAGNI.
  7. Keep diffs as minimal as possible.

Message Content

LLMMessage.content is str | list[dict[str, Any]] | None; the list form is multimodal content parts. Never str() it — that puts a Python repr ([{'type': 'text', 'text': 'hi'}]) in front of the model and into memory. Collapse a message to text with the helper instead:

from crewai.utilities.agent_utils import message_content_text

text = message_content_text(msg)  # "" for None; joined text for a parts list

Parts arrive from a model and are typed dict[str, Any], so a text key that is not a string is possible. _content_parts_text skips those blocks rather than raising, and names a list with no usable text [multimodal content].

Changing Docs

  1. Edit MDX under docs/edge/en/* and reference it from docs/docs.json if needed.
  2. Do not modify files under docs/v*/. Those are frozen release snapshots managed by devtools.
  3. Do not delete or rename files under docs/images/ as frozen snapshots may reference them.
  4. If you want to preview your changes locally, use cd docs && mintlify dev. To check for broken links, run cd docs && mintlify broken-links.
  5. After editing English docs, sync translations to ar, ko, and pt-BR before finishing the task. Follow DOCS_TRANSLATIONS.md.
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 · 46 lines · 452 tokens per session scan A 03a3efb0ebb1

Subscribe to this mod's changes

crewAI AGENTS.md is an instructions file published in the GitHub repository crewAIInc/crewAI (60,549 stars, last pushed today), licensed MIT. It adds 452 tokens to every session, about $0.0018 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

crewAI AGENTS.md compared with instructions from other repositories

crewAI AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
crewAI AGENTS.mdcrewAIInc/crewAIInstructions file61ktodayMITA452Codex, 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