What is graflow AGENTS.md?

Repository instructions for GraflowAI/graflow, a Python workflow system with task execution, queues, workers, APIs, human feedback, and tracing.

Working in the Graflow repository: locating modules and tests, installing dependencies, formatting code, running lint checks, and following its development guidelines.

They give coding agents the project’s expected structure, commands, naming style, and testing approach before making changes.

How GraflowAI/graflow configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to GraflowAI/graflow. 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/GraflowAI/graflow/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/GraflowAI/graflow

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/graflowai/graflow/agents-md/github.svg)](https://agentmods.dev/instructions/graflowai/graflow/agents-md)

Your own site

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

Per session 757 This file is loaded in full into every session.

When invoked 757 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	$0.00757	$0.00757
Opus 5.5	$0.00303	$0.00303
Sonnet 5.5	$0.00151	$0.00151
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash 1f7b498e0336, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graflow 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

graflow/: Source code.
- core/: Workflow engine, tasks, graph, decorators, handlers, checkpoints.
- channels/: In‑memory/Redis channels and typing helpers.
- queue/: In‑memory/Redis task queues.
- coordination/: Coordinators, executors, multiprocessing/Redis integration.
- worker/: Worker entrypoints and handlers.
- hitl/: Human-in-the-Loop (HITL) feedback management.
- llm/: LLM integration and agent management.
- trace/: Tracing and observability (Langfuse integration).
- api/: REST API for workflow management and HITL feedback.
- serialization/: Task serialization utilities.
- debug/: Debugging and visualization tools.
- utils/, exceptions.py, __init__.py.
tests/: Pytest suite by domain (e.g., core/, queue/, scenario/, integration/).
examples/: Runnable examples (e.g., examples/simple_workflow_example.py).
docs/: Architecture notes and dev plans.

Build, Test, and Development Commands

make install / make install-dev: Sync deps with uv (dev adds lint/test tools).
make format: Auto‑fix common style issues via ruff.
make lint: Run ruff and mypy.
make check: Type check only (mypy).
make test: Run unit tests (pytest -v).
make test-cov: Run tests with coverage report.
make check-all: Format, lint, and test.
make py examples/simple_test.py: Run a file with PYTHONPATH=. using uv.

Prereqs: Python 3.11+, uv installed. Examples using Redis assume a local Redis at localhost:6379.

Coding Style & Naming Conventions

Indentation: 4 spaces; max line length: 120.
Types: Add explicit annotations (mypy is strict on untyped defs).
Naming: snake_case for functions/vars, PascalCase for classes, module names lowercase.
Imports: Group and sort (ruff/isort settings; first‑party is graflow).

Testing Guidelines

Framework: pytest. Tests live under tests/ and follow test_*.py naming.
Markers: @pytest.mark.integration for external‑service tests (e.g., Redis). Example: uvx pytest -m 'not integration'.
Run: make test locally before PRs. Use make test-cov for coverage when changing core logic.

Read the full file on GitHub · 52 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 · 52 lines · 757 tokens per session scan A 1f7b498e0336

Subscribe to this mod's changes

graflow AGENTS.md is an instructions file published in the GitHub repository GraflowAI/graflow (41 stars, last pushed 13d ago), licensed Apache-2.0. It adds 757 tokens to every session, about $0.0030 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.

LLM Planning Testing agentic-workflow agents ai-agents workflow workflow-engine

graflow AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
graflow AGENTS.mdGraflowAI/graflow	Instructions file	41	13d ago	Apache-2.0	A	757	Codex, OpenCode
flow-like copilot-instructions.mdRheosoph/flow-like	Instructions file	972	yesterday	none	A	1,349	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	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

graflow: Instructions file for Codex