Product-to-Prod: Instructions file for Claude Code

AGENTS.md

Product-to-Prod AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from naderelewa/Product-to-Prod. It costs 2,913 tokens per session, scanned A, original, MIT.

A set of instructions for an AI coding agent working on product management tasks such as requirements, prioritisation, launch planning, and checking results after release.

In plain words
What is it for?
It helps with product requirements, prioritising a group of requests, preparing handoff materials, planning launches, and reviewing whether released work achieved its intended result.
Why use it?
It gives the agent a fixed process for turning product decisions into evidence-backed work, while marking claims that lack supporting evidence.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT variable, but also the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is naderelewa/Product-to-Prod's own configuration. It tells Claude Code, Codex and OpenCode how to work on Product-to-Prod itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Product-to-Prod configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to naderelewa/Product-to-Prod. 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/naderelewa/Product-to-Prod/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/naderelewa/Product-to-Prod

Made for: Claude Code, 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.

agentmods badge for Product-to-Prod AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/naderelewa/product-to-prod/agents-md/github.svg)](https://agentmods.dev/instructions/naderelewa/product-to-prod/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/naderelewa/product-to-prod/agents-md"><img src="https://agentmods.dev/badge/instructions/naderelewa/product-to-prod/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.

agentmods 80×15 button for Product-to-Prod AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/naderelewa/product-to-prod/agents-md"><img src="https://agentmods.dev/badge/instructions/naderelewa/product-to-prod/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,913 This file is loaded in full into every session.
When invoked 2,913 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02913 $0.02913
Opus 5 $0.01456 $0.01456
Sonnet 5 $0.00583 $0.00583
Haiku 4.5 $0.00291 $0.00291

Measured 12d ago against content hash fd2bcc73c210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Product-to-Prod 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 12d 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 · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For agents running this plugin

This file is the whole protocol in one place, so that a harness which does not auto-load plugin skills still runs the engine correctly. If your harness reads skill metadata (name, description, triggers) on its own, use it, and treat this file as the spine those skills share. If it does not, this file plus skills/pm-start/SKILL.md is enough to start: read this, read that, route, and open the routed verb's own file when you get there.

You are helping somebody decide what to build and prove whether it worked. The work is product management: requirements, prioritisation, go-to-market, post-release verification. The engine's value is not that it writes documents quickly. It is that every claim in what it writes is either sourced or labelled as unsourced, and that no gate is passed by the agent that wants to pass it.

What ships here

Piece What it is
skills/pm-start/ the dispatcher: interviews in plain words, locks context, routes to exactly one verb
skills/pm-requirements-v1/ a feature from strategy statement to an evidence-tagged handoff package
skills/pm-portfolio-v1/ a batch of asks to a scored, prioritised verdict
skills/pm-gtm-v1/ a go-to-market plan, config-only, no spend and no platform writes
skills/pm-verify-release-v1/ a shipped release graded against its pre-declared acceptance scenarios
skills/gtm-domain-library/ the generic framework library the verbs open one section at a time
skills/init/ first-run setup, including the off-by-default local logging consent
scripts/ the mechanical gates: preflight.sh, hostcheck.sh, tag-lint.sh, inference-gate.sh, publish-lint.sh, release.sh, telemetry.sh
config/ packs.json (context registry) · local.template.json (every host-specific key, all null) · dependencies.json (per-verb capabilities) · denylist.txt (the publish gate's rules)
packs/ the context-pack mechanism, shipping one fictional template pack
docs/ the six documents the README opens into: the wizard and package anatomy, outputs, examples by industry, configuration, the full comparison, the usage log
everything else at the root .claude-plugin/plugin.json (what a harness reads to install this), config.schema.json, README.md, AGENTS.md, LICENSE, .gitignore, references/ (shared reference files) and tests/ (the check suite)

Read the full file on GitHub · 169 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. 12d ago First seen · 169 lines · 2,913 tokens per session scan A fd2bcc73c210

Subscribe to this mod's changes

Product-to-Prod AGENTS.md is an instructions file published in the GitHub repository naderelewa/Product-to-Prod (43 stars, last pushed yesterday), licensed MIT. It adds 2,913 tokens to every session, about $0.0146 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 2026-08-30.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens