A planning check for software tasks created from a larger project goal, called an epic. It verifies that each task records important path choices, open questions, and agreements between parts of the system before coding begins.

Use it to review all tasks in an epic, identify missing planning information, and save the findings. Run it with `/pm:plan-review `, such as `/pm:plan-review user-auth`.

It helps catch unclear or incomplete tasks before implementation starts. It also records the review results on the tasks for later reference.

plan-review — Command for Claude Code by dtannen: A planning check for software tasks created from a…

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 commands/dtannen/pm/plan-review

Clone the repo

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

Made for: Claude Code.

Or install pm, the plugin that ships this one along with the rest of its 4 skills, 13 commands, 5 agents, 3 hooks, 1 MCP server.

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/commands/dtannen/pm/plan-review.svg)](https://agentmods.dev/commands/dtannen/pm/plan-review)

Your own site

<a href="https://agentmods.dev/commands/dtannen/pm/plan-review"><img src="https://agentmods.dev/badge/commands/dtannen/pm/plan-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 890 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00890
Opus 5	$0.00006	$0.00445
Sonnet 5	$0.00003	$0.00178
Haiku 4.5	$0.00001	$0.00089

Measured 4d ago against content hash d744e79aee12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-review 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 4d 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.

.claude-plugin/commands/plan-review.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RA Planning Review

Validate that tasks derived from an epic include the RA Planning block (path decisions, planning uncertainties, and interface contracts) before implementation starts.

Usage

/pm:plan-review <epic-name>

Example: /pm:plan-review user-auth

Instructions

You are running a lightweight RA planning review for the epic: $ARGUMENTS

MCP Integration (preferred)

Use MCP to enumerate tasks under the epic and persist review findings.

Full name: mcp__project-manager-mcp__list_epics — Resolve the epic
Full name: mcp__project-manager-mcp__list_tasks — List tasks for the epic
Full name: mcp__project-manager-mcp__get_task_details — Read current planning metadata
Full name: mcp__project-manager-mcp__update_task — Persist review results and logs

Recommended flow:

Resolve epic via mcp__project-manager-mcp__list_epics.
Fetch tasks for that epic via mcp__project-manager-mcp__list_tasks(epic_id|epic_name).
After agent review, write a concise log_entry and store findings under ra_metadata.planning_review via ...__update_task for each task.
If trivial fixes are auto-applied to local files, reflect that in MCP logs as well.

1. Validate Inputs

Prefer MCP: resolve epic and enumerate tasks using MCP functions above.
Fallback: check .pm/epics/$ARGUMENTS.md and list .pm/tasks/*$ARGUMENTS*.md.
If no tasks found: suggest running /pm:epic-tasks $ARGUMENTS.

2. Deploy Planning Reviewer Agent

Use the Task tool to deploy the planning-reviewer agent and scan all matching tasks:

Task:
  description: "RA planning readiness review for epic $ARGUMENTS"
  subagent_type: "general-purpose"
  prompt: |
    You are the planning-reviewer agent. Validate that every task for epic "$ARGUMENTS" is RA-ready.

    FILES TO REVIEW:
    - Epic: .pm/epics/$ARGUMENTS.md
    - Tasks: .pm/tasks/*$ARGUMENTS*.md

    CHECKLIST:
    1) RA Planning section exists in each task
    2) Path decisions present where applicable:
       - Use `#PATH_DECISION: <topic>`
       - Record a chosen option and a brief decision rationale
    3) Planning uncertainties enumerated:
       - Use `PLAN_UNCERTAINTY: <item>` per uncertainty
       - If none, include explicit `PLAN_UNCERTAINTY: None`
    4) Interface contracts are explicit and testable:
       - Endpoints/APIs listed
       - Request/Response schemas or data types
       - Error cases/versioning notes
    5) No "TBD" placeholders for interfaces

    TAG POLICY:
    - Only use planning tags: `#PATH_DECISION`, `PLAN_UNCERTAINTY`
    - Do NOT add implementation tags (e.g., `#COMPLETION_DRIVE_*`)

    OUTPUTS:
    - Produce a concise "RA Planning Review Summary" with file-by-file READY/REQUIRES_UPDATES status
    - For trivial omissions (e.g., explicit `PLAN_UNCERTAINTY: None`), you may amend task files directly
    - For larger gaps, propose exact edits without implementing them
    - Finish with a single decision line: READY_TO_IMPLEMENT or REQUIRES_UPDATES

Read the full file on GitHub · 87 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.

4d ago First seen · 87 lines · 13 tokens per session scan A d744e79aee12

Subscribe to this mod's changes

plan-review is a command published in the GitHub repository dtannen/pm (0 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 890 once invoked, about $0.0001 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.

Planning

plan-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

RA Planning Review

Usage

Instructions

MCP Integration (preferred)

1. Validate Inputs

2. Deploy Planning Reviewer Agent

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze