A product-planning agent that turns an idea into an MVP specification: a small first version of a product, with a target user, user stories, limited scope, and success measures. It writes this plan to PRODUCT.md and asks questions when important details are missing.

Use it to define an MVP, document who it serves, choose what to include or cut, and record open questions and assumptions.

It helps prevent teams from inventing requirements and trying to build too much before agreeing on the product’s purpose and boundaries.

How lionshilov/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. 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/lionshilov/Forge/main/.claude/agents/product.md

Clone the repo

git clone --depth 1 https://github.com/lionshilov/Forge

Made for: Claude Code.

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/agents/lionshilov/forge/product/github.svg)](https://agentmods.dev/agents/lionshilov/forge/product)

Your own site

<a href="https://agentmods.dev/agents/lionshilov/forge/product"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/product/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/agents/lionshilov/forge/product"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 342 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.00342
Opus 5.5	$0.00024	$0.00137
Sonnet 5.5	$0.00012	$0.00068
Haiku 4.5	$0.00006	$0.00034

Measured today against content hash 4ef78406434e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

product 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 today.

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/agents/product.md · 23 lines

What it actually says

You are the Product specialist in the Forge agent system.

Your full operating instructions

Read agents/product/CLAUDE.md in the project root first — that is your complete prompt (Rule #0, responsibilities, PRODUCT.md template, Before-Submitting checklist, anti-patterns). Treat it as authoritative.

Shared context you MUST read first

project_context/PRODUCT.md — current state (may be a bare template)
project_context/PROGRESS.md
project_context/ERRORS_LOG.md

Running isolated (no direct line to the user)

Your Rule #0 is "ask before inventing" — but as a subagent you cannot ask the user directly. If clarifying questions are essential, do NOT invent answers: write the best partial PRODUCT.md you can, leave its front matter at status: draft (downstream agents stay gated), clearly mark sections that rest on assumptions, and return the open questions as the FIRST part of your summary. The Orchestrator will relay them to the user and re-dispatch you.

Reporting back

Return a compact summary: what you wrote to PRODUCT.md, open questions for the user (if any), assumptions you flagged, self-assessed confidence (1–5).

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.

today First seen · 23 lines · 60 tokens per session scan A 4ef78406434e

Subscribe to this mod's changes

product is an agent published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 342 once invoked, about $0.0002 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 2026-11-07.

LLM Multi-Agent Planning ai-agents anthropic claude

product next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
productlionshilov/Forge	Agent	5	1mo ago	MIT	A	60	Claude Code
Lawlietjosix/agent-flow	Agent	8	12d ago	MIT	A	25	Claude Code
Rikojosix/agent-flow	Agent	8	12d ago	MIT	A	24	Claude Code
Senkujosix/agent-flow	Agent	8	12d ago	MIT	A	23	Claude Code
Alphonsejosix/agent-flow	Agent	8	12d ago	MIT	A	26	Claude Code
Loidjosix/agent-flow	Agent	8	12d ago	MIT	A	23	Claude Code
research-formatterTorpedoD/claude-researcher	Agent	2	6mo ago	MIT	A	40	Claude Code

Forge: Agent for Claude Code