What is pm AGENTS.md?

A set of AGENTS.md instructions for a Python project manager with a dashboard and an MCP server, which lets agents coordinate projects, larger work items, and tasks.

Use it when contributing to the project or integrating agents with it. It covers the FastAPI backend, SQLite database, command-line interface, dashboard, and task-management MCP tools.

It explains the repository’s structure and the expected way for agents to find work, lock tasks, update progress, and follow the project’s response-awareness method.

How dtannen/pm configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to dtannen/pm. 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/dtannen/pm/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dtannen/pm

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/dtannen/pm/agents-md/github.svg)](https://agentmods.dev/instructions/dtannen/pm/agents-md)

Your own site

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

Per session 1,453 This file is loaded in full into every session.

When invoked 1,453 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	$0.01453	$0.01453
Opus 5.5	$0.00581	$0.00581
Sonnet 5.5	$0.00291	$0.00291
Haiku 4.5	$0.00145	$0.00145

Measured 2mo ago against content hash 3ce2f12b12eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents integrating with this repository. It explains what this repo is, how to interact with it via MCP tools, and how to apply the Response Awareness (RA) methodology while working.

What This Repo Is

This project is a Python-based project/epic/task manager with a real-time dashboard and an MCP (Model Context Protocol) server so agents can collaborate programmatically.

Name: project-manager-mcp
Backend: FastAPI + WebSockets (MCP + updates)
DB: SQLite (WAL), schema for projects → epics → tasks (+ task logs)
CLI: project-manager-mcp plus python -m task_manager.cli
Dashboard: single-page UI served by the backend
MCP Tools: create/update/list tasks, acquire/release locks, RA tagging, etc.

See README.md for installation, usage, and architecture details.

MCP: How Agents Integrate

The server exposes a set of MCP tools that agents call to query, plan, execute, and verify work. Common tools include:

get_available_tasks: Find work by status, exclude locked tasks
acquire_task_lock: Atomically lock a task (moves status to IN_PROGRESS)
update_task_status: Single-call status change with auto-locking
release_task_lock: Explicitly release a held lock
create_task / update_task: CRUD with full RA metadata support
get_task_details: Full task + logs + dependencies
list_projects / list_epics / list_tasks: Hierarchical queries
add_ra_tag: Create RA tags with automatic context capture

Transport modes:

stdio (default): for local/CLI integration
sse: HTTP SSE endpoint for network clients

Refer to README.md and docs/ for details and examples.

Start With A Task (Required)

Before you do any work, you must create or select a task to work on.

Why: Ensures ownership, locking, logging, RA tags, and status tracking.
How:
- MCP: create_task with name, description, and epic_id/project_id (optionally set ra_mode/ra_score).
- Dashboard: Create a task via the UI in the correct project/epic.
- Scope: If your work spans multiple concerns, split into separate tasks.
Then: Acquire a lock (acquire_task_lock) before making changes, or rely on single-call update_task_status for short operations (auto-locking).

Read the full file on GitHub · 144 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 · 144 lines · 1,453 tokens per session scan A 3ce2f12b12eb

Subscribe to this mod's changes

pm AGENTS.md is an instructions file published in the GitHub repository dtannen/pm (0 stars, last pushed 1y ago), licensed MIT. It adds 1,453 tokens to every session, about $0.0058 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 2026-08-31.

Project management

pm AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pm AGENTS.mddtannen/pm	Instructions file	0	1y ago	MIT	A	1,453	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	today	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

pm: Instructions file for Codex