What is agent-graph AGENTS.md?

Repository instructions for developers and coding agents working on a Python backend, JavaScript frontend, documentation, infrastructure, tests, and release packaging.

Use them when developing or maintaining the project, including running FastAPI, the Vite frontend, MongoDB and MinIO services, tests, documentation builds, linting, and packaging.

They provide the commands and conventions needed to set up the project, run its parts, check changes, and prepare releases without guessing the workflow.

How keta1930/agent-graph configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to keta1930/agent-graph. 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/keta1930/agent-graph/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/keta1930/agent-graph

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/keta1930/agent-graph/agents-md/github.svg)](https://agentmods.dev/instructions/keta1930/agent-graph/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/keta1930/agent-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/keta1930/agent-graph/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/keta1930/agent-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/keta1930/agent-graph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 515 This file is loaded in full into every session.

When invoked 515 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	$0.00515	$0.00515
Opus 5.5	$0.00206	$0.00206
Sonnet 5.5	$0.00103	$0.00103
Haiku 4.5	$0.00052	$0.00052

Measured 2mo ago against content hash a707c24d6022, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-graph 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This file provides guidance to AI coding agents when working with code in this repository.

Commands

Backend (Python 3.11+, uv):

uv sync — install dependencies
uv run --env-file .env fastapi run — start the production API server using PORT
uv run --env-file .env fastapi dev — start the development API server with reload
python agent_graph/scripts/generate_jwt_secret.py — generate JWT secret key
uv run pytest — run tests (unit in tests/unit/, integration in tests/integration/)

Frontend (Node, npm):

cd frontend && npm install && npm run dev — start Vite using the root .env
npm run build — production build outputs to agent_graph/dist/
npm run lint — ESLint with TypeScript strict rules

Infrastructure:

docker compose --env-file .env -f docker/docker-compose.yml up -d — start MongoDB, Mongo Express, and MinIO (reads config from root .env)

Docs:

mkdocs build --strict — build the documentation site and fail on warnings

Release packaging:

cd frontend && npm ci && npm run build — refresh the frontend assets in agent_graph/dist/
Run uv build from the repository root after the frontend build — create wheel and sdist with the current frontend assets

Architecture

FastAPI serves both REST API (/api/) and the pre-built frontend from agent_graph/dist/
All config lives in a single root .env (backend settings + MongoDB/MinIO container params). Copy .env.example to .env and fill in values before first run; both the API server and docker compose --env-file .env read from it.
The backend, frontend, and internal MCP client ports are configured through the root .env.
Auth uses JWT access + refresh tokens; three roles: super_admin, admin, normal

Git conventions

GitHub Flow: feature branches off master, PR with review before merge.

Test and format infrastructure

Backend tests use pytest; run with uv run pytest. Unit tests live in tests/unit/, integration tests in tests/integration/.
Coverage is available on demand: uv run pytest --cov=agent_graph.
No Python formatter or linter is configured. ESLint is frontend-only.

Read the full file on GitHub · 43 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 · 43 lines · 515 tokens per session scan A a707c24d6022

Subscribe to this mod's changes

agent-graph AGENTS.md is an instructions file published in the GitHub repository keta1930/agent-graph (237 stars, last pushed 26d ago), licensed Apache-2.0. It adds 515 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.

agent agentic-framework agentic-workflow graph mcp

agent-graph AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-graph AGENTS.mdketa1930/agent-graph	Instructions file	237	26d ago	Apache-2.0	A	515	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	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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-graph: Instructions file for Codex