agentmods.dev

agent-graph AGENTS.md

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

In plain words
What is it for?
Use them when developing or maintaining the project, including running FastAPI, the Vite frontend, MongoDB and MinIO services, tests, documentation builds, linting, and packaging.
Why use it?
They provide the commands and conventions needed to set up the project, run its parts, check changes, and prepare releases without guessing the workflow.

Instructions file for CodexOpenCode

221 24d ago A scan 515 tokens original Apache-2.0
View the source file keta1930/agent-graph
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/keta1930/agent-graph/agents-md
Clone the repo
git clone --depth 1 https://github.com/keta1930/agent-graph

Made for: Codex, OpenCode.

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. Scan, not verified.
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 $0.00515 $0.00515
Opus 5 $0.00258 $0.00258
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash a707c24d6022, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

  1. 2d 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 (221 stars, last pushed 24d ago), licensed Apache-2.0. It adds 515 tokens to every session, about $0.0026 per session on Opus 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.

FrontendGit and workflowTestingagentagentic-frameworkagentic-workflowgraphmcp
Related

Other instructions, from other repositories

deer-flow AGENTS.md

AGENTS.md instructions for bytedance/deer-flow, covering agents.md, what is deerflow, service topology, repository map and commands: root vs. module.

bytedance/deer-flow · 3,430 tokens

deer-flow copilot-instructions.md

Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.

bytedance/deer-flow · 1,714 tokens

deer-flow CLAUDE.md

Claude Code instructions for bytedance/deer-flow: The repo's agent guidance lives in AGENTS.md so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below.

bytedance/deer-flow · 50 tokens

nexent AGENTS.md

AGENTS.md instructions for ModelEngine-Group/nexent, covering agents, available skills, project overview, developer commands and backend (python 3.11).

ModelEngine-Group/nexent · 1,369 tokens

turbo-flow CLAUDE.md

Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.

marcuspat/turbo-flow · 158 tokens

sprawling CLAUDE.md

Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.

2youg1/sprawling · 83 tokens