What is agentpool AGENTS.md?

Repository instructions for AgentPool, a framework that configures and coordinates different AI agents with YAML files. They document setup, testing, and code-quality commands.

Use them to install the project with uv, run its unit or integration tests, measure coverage, and check code quality.

They give contributors the project's expected installation and verification steps instead of leaving those commands unclear.

agentpool AGENTS.md — Instructions file by phil65

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/phil65/agentpool/agents-md

Clone the repo

git clone --depth 1 https://github.com/phil65/agentpool

Made for: Codex, OpenCode.

Per session 3,580 This file is loaded in full into every session.

When invoked 3,580 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.

Model	Per session	Once invoked
Fable 5	$0.03580	$0.03580
Opus 5	$0.01790	$0.01790
Sonnet 5	$0.00716	$0.00716
Haiku 4.5	$0.00358	$0.00358

Measured yesterday against content hash a719027edc36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentpool 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 yesterday.

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 · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

AgentPool is a unified agent orchestration framework that enables YAML-based configuration of heterogeneous AI agents. It bridges multiple protocols (ACP, AG-UI, OpenCode, MCP) and supports native PydanticAI agents, Claude Code agents, Goose, and other external agents.

Core Philosophy: Define once in YAML, expose through multiple protocols, enable seamless inter-agent collaboration.

Development Commands

Installation & Setup

# Install with uv (recommended)
uv sync --all-extras

# Install specific extras
uv sync --extra coding --extra server

Testing

# Run all tests (excludes slow and acp_snapshot by default)
uv run pytest

# Run with coverage
uv run pytest --cov-report=xml --cov=src/agentpool/ --cov-report=term-missing

# Run specific test markers
uv run pytest -m unit          # Unit tests only
uv run pytest -m integration   # Integration tests only
uv run pytest -m slow          # Include slow tests
uv run pytest -m acp_snapshot  # ACP snapshot tests

# Run single test file
uv run pytest tests/test_specific.py

# Run with verbose output
uv run pytest -vv

# Run tests in parallel
uv run pytest -n auto

Code Quality


# Main command: runs all

duty lint

# Lint with ruff
uv run ruff check src/

# Format check
uv run ruff format --check

# Format code
uv run ruff format src/

# Type checking with mypy
uv run --no-group docs mypy src/

Running AgentPool

# Run agent directly
agentpool run <agent_name> "prompt text"

# Start ACP server (for IDEs like Zed)
agentpool serve-acp config.yml

# Start OpenCode server
agentpool serve-opencode config.yml

# Start MCP server
agentpool serve-mcp config.yml

# Start AG-UI server
agentpool serve-agui config.yml

# Start OpenAI-compatible API server
agentpool serve-api config.yml

# Watch for triggers
agentpool watch --config agents.yml

# View analytics
agentpool history stats --group-by model

Code Architecture

Module Structure

The codebase is organized into focused packages under src/:

Read the full file on GitHub · 475 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.

yesterday First seen · 475 lines · 3,580 tokens per session scan A a719027edc36

Subscribe to this mod's changes

agentpool AGENTS.md is an instructions file published in the GitHub repository phil65/agentpool (184 stars, last pushed 4mo ago), licensed MIT. It adds 3,580 tokens to every session, about $0.0179 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.

Code review Data and AI LLM Testing agent ai llm-agent pydantic yaml

agentpool AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Project Overview

Development Commands

Installation & Setup

Testing

Code Quality

Running AgentPool

Code Architecture

Module Structure

What this file has done since we first saw it

Other instructions, from other repositories

agentscope copilot-instructions.md

AReaL AGENTS.md

AReaL CLAUDE.md

DM-Code-Agent AGENTS.md

braindb CLAUDE.md

vetix AGENTS.md