product-plan

product-plan is a skill for Claude Code from blake-simpson/belmont. It costs 17 tokens per session (7,818 once invoked), scanned A, original, Apache-2.0.

An interactive planning session that creates a product requirements document (PRD) and a progress tracker for a feature. It asks questions until the feature’s goals and implementation plan are clear.

In plain words
What is it for?
Use it to define a new Belmont feature, record its requirements, and create its initial progress files inside the .belmont directory.
Why use it?
It turns an incomplete idea into an agreed written plan before coding begins. This helps prevent unclear requirements and keeps planning separate from source-code changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the belmont plugin — 17 skills shipped together

Good fit Use it to define a new Belmont feature, record its requirements, and create its initial progress files inside the .belmont directory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blake-simpson/belmont/product-plan
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.

Any agent
npx skills add blake-simpson/belmont --skill product-plan
Clone the repo
git clone --depth 1 https://github.com/blake-simpson/belmont

Made for: Claude Code.

Or install belmont, the plugin that ships this one along with the rest of its 17 skills.

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.

agentmods badge for product-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/blake-simpson/belmont/product-plan/github.svg)](https://agentmods.dev/skills/blake-simpson/belmont/product-plan)
Your own site
<a href="https://agentmods.dev/skills/blake-simpson/belmont/product-plan"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/product-plan/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.

agentmods 80×15 button for product-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/blake-simpson/belmont/product-plan"><img src="https://agentmods.dev/badge/skills/blake-simpson/belmont/product-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,818 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.07818
Opus 5 $0.00009 $0.03909
Sonnet 5 $0.00003 $0.01564
Haiku 4.5 $0.00002 $0.00782

Measured 9d ago against content hash 566a237f384f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-plan 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 9d 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.

plugin/skills/product-plan/SKILL.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Belmont: Product Plan

You are running an interactive planning session. Your goal is to work with the user to create a comprehensive PRD (Product Requirements Document) and PROGRESS tracking file.

This session requires ultrathink-level reasoning — deeply consider product edge cases, user needs, and architectural implications before proposing structure.

CRITICAL RULES

  1. This is ONLY a planning session. Do NOT implement anything.
  2. Do NOT create or edit any source code files (no .tsx, .ts, .css, etc.).
  3. ONLY write to files in .belmont/ (PRD.md, PROGRESS.md, and feature directories).
  4. Ask questions iteratively until the plan is 100% concrete.
  5. Always ask the user for clarification and approval before finalizing.

Codex Plan-Mode Preflight

Codex exposes keyboard-navigable structured questions through plan-mode planning turns. If you are Codex and the structured question tool is unavailable in the current turn, STOP before asking any planning questions or editing files. Tell the user to restart this skill with:

/plan $belmont:product-plan <brief>

Do NOT fake the structured question flow with Markdown lists. The user must be able to navigate the pick-list with arrow keys.

Codex write handoff

This section is Codex-only. It does not apply to Claude Code, opencode, Cursor, Windsurf, Gemini, GitHub Copilot, Pi, or other agents that can both ask structured questions and write files in the same session.

If you are Codex in plan mode and file editing is unavailable or inappropriate for the current planning turn:

  1. Complete the full structured interview exactly as this skill requires.
  2. Prepare the final .belmont/ file contents or precise section updates.
  3. Instead of writing files directly, output a single fenced BELMONT_PLAN_PACKET for $belmont:codex-plan-apply.
  4. Tell the user to exit plan mode and run:
    $belmont:codex-plan-apply
    

The packet must include every target .belmont/ path, each operation (create, replace, or update-section), complete content for creates/replacements, exact section content for updates, the commit message, and the next recommended Belmont prompt. Do not leave decisions only in chat.

Read the full file on GitHub · 511 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 511 lines · 17 tokens per session scan A 566a237f384f

Subscribe to this mod's changes

product-plan is a skill published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 21d ago), licensed Apache-2.0. It adds 17 tokens to every session and 7,818 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.