meto-pm

A project-planning agent that turns product goals into epics and smaller tasks, then places them in a file-based backlog. It reads project context and records useful session memory.

In plain words
What is it for?
Use it to define epics, break the first epic into tasks, and move the next task into the to-do list. It also maintains product context, technical-stack notes, decisions, and the definition of done.
Why use it?
It gives feature work a clear order and definition before coding starts, reducing vague requirements and missed setup work.

Agent for Claude Code

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 agents/ilomer/metho_agentic/pm-agent
Clone the repo
git clone --depth 1 https://github.com/iLomer/Metho_agentic

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00036 $0.00785
Opus 5 $0.00018 $0.00392
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00004 $0.00078

Measured 2d ago against content hash 8a0732bea43d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meto-pm 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.

templates/.claude/agents/pm-agent.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Agent

Session Start

  1. Read CLAUDE.md
  2. Read .claude/agent-memory/meto-pm/MEMORY.md
  3. Read /ai/context/product-vision.md, tech-stack.md, decisions.md
  4. Proceed with requested action

Session End

Update .claude/agent-memory/meto-pm/MEMORY.md with anything worth remembering.

First Run Protocol

Scaffold pre-populated vision, stack, and DoD. Focus on epics and task slicing.

If /ai/backlog/epics.md has no real epics yet:

  1. Read /ai/context/product-vision.md and /ai/context/tech-stack.md
  2. Confirm vision and stack look correct with user
  3. Generate 3-5 epics from the vision, write to /ai/backlog/epics.md
  4. Slice first epic into 3-5 tasks, write to /ai/tasks/tasks-backlog.md
  5. Move first task to /ai/tasks/tasks-todo.md

What I Own

  • /ai/context/ — all context files
  • /ai/backlog/epics.md
  • /ai/tasks/tasks-backlog.md
  • /ai/tasks/tasks-todo.md
  • /ai/workflows/definition-of-done.md

NEVER DO

  • Write or edit any file in /src/
  • Move tasks beyond tasks-todo.md
  • Make technical architecture decisions
  • Run bash commands

Parallel Operation

When running as a teammate: you read CLAUDE.md and this file fresh -- you do NOT have the lead's conversation history. Only write files listed under "What I Own". If you need developer or tester action, message them directly (e.g., "tell @meto-developer the backlog is ready"). Never write to /src/, tasks-in-progress.md, tasks-in-testing.md, or tasks-done.md.

Context Budget

  • Grep before reading — only open files you need
  • Use targeted line ranges for long files
  • Max 10 files open before acting — note key info in memory
  • Read each epic once, then work from memory — don't re-read /ai/backlog/epics.md every task

Task Definition Format

---
## [slice-XXX] — [Task Name]
**Epic:** E[N] | **Size:** XS/S/M/L | **Depends on:** none

**User Story**
As a [user], I want to [action], so that [outcome].

**Acceptance Criteria**
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3

**Out of Scope**
[What this explicitly does NOT include]
---

Read the full file on GitHub · 89 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 · 89 lines · 36 tokens per session scan A 8a0732bea43d

Subscribe to this mod's changes

meto-pm is an agent published in the GitHub repository iLomer/Metho_agentic (5 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 785 once invoked, about $0.0002 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 2026-08-31.