agentmods.dev

create-agentic-product: Instructions file for Claude Code

CLAUDE.md

create-agentic-product CLAUDE.md is an instructions file for Claude Code from fltman/create-agentic-product. It costs 1,676 tokens per session, scanned A, original, MIT.

Project-specific instructions for create-agentic-product, a project that uses a creative product team of AI agents. They describe how to understand a user's needs and assemble the right team.

In plain words
What is it for?
Following the project's product-development process, interpreting user needs, and selecting an AI agent team.
Why use it?
They give the coding agent the project's intended workflow, which helps it choose appropriate roles before working on a product request.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is fltman/create-agentic-product's own configuration. It tells Claude Code how to work on create-agentic-product 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 create-agentic-product configures →

not rated 48repo 9d ago A scan 1,676 tokens original MIT
View source ↗ fltman/create-agentic-product
Reuse

Borrowing it

Nothing to install: this file belongs to fltman/create-agentic-product. 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/fltman/create-agentic-product/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/fltman/create-agentic-product

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.

agentmods badge for create-agentic-product CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fltman/create-agentic-product/claude-md/github.svg)](https://agentmods.dev/instructions/fltman/create-agentic-product/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fltman/create-agentic-product/claude-md"><img src="https://agentmods.dev/badge/instructions/fltman/create-agentic-product/claude-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 create-agentic-product CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fltman/create-agentic-product/claude-md"><img src="https://agentmods.dev/badge/instructions/fltman/create-agentic-product/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,676 This file is loaded in full into every session.
When invoked 1,676 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 $0.01676 $0.01676
Opus 5.5 $0.00670 $0.00670
Sonnet 5.5 $0.00335 $0.00335
Haiku 4.5 $0.00168 $0.00168

Measured 2mo ago against content hash 73d887c1b71e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-agentic-product CLAUDE.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 2mo 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.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Creative Product Team

Vad det här projektet handlar om

Det här är ett ramverk för att snabbt sätta upp ett AI-drivet kreativt team som hjälper användaren ta en produktidé från koncept till lansering. Teamet består av specialiserade agenter som samarbetar i faser.

Arbetsflöde

Steg 1: Förstå användarens behov

Innan något annat — förstå vad användaren vill bygga. Ställ frågor om:

  1. Produkt: Vad är det för produkt/tjänst? Fysisk, digital, hybrid?
  2. Målgrupp: Vem är den för? Geografi, demografi, beteende?
  3. Marknader: Vilka länder/regioner? En marknad eller flera?
  4. Ambition: MVP/test eller full lansering?
  5. Budget: Indikativ nivå — påverkar strategi och kanalval
  6. Tidplan: När ska det vara klart?
  7. Befintligt material: Finns det redan research, design, copy, kod?

Baserat på svaren, sätt ihop rätt team. Inte alla agenter behövs för varje projekt.

Steg 2: Sätt ihop rätt team

Teamet ska skräddarsys för varje projekt. Baserat på användarens produkt, marknad och mål — föreslå vilka agenter som behövs. Var kreativ och tänk bortom standardrollerna.

Alltid med
  • project-lead — Koordinerar allt, driver framåt, kvalitetssäkrar
Exempelroller (använd som inspiration, inte checklista)

Research & Strategi: competitor-analyst, market-researcher, cultural-analyst, legal-analyst Koncept & Design: brand-strategist, product-designer, art-director, copywriter Digital: frontend-dev, backend-dev Lansering & Tillväxt: marketer, social-media-strategist

Men lägg gärna till agenter som passar projektet — t.ex. en sustainability-advisor för gröna produkter, en pricing-strategist för SaaS, en packaging-designer för fysiska varor, en community-manager för plattformsprodukter, eller helt nya roller som projektet kräver.

Förklara för användaren vilka agenter du föreslår och varför. Låt dem justera teamet innan arbetet börjar.

Steg 3: Kör faserna

Varje fas bygger på den förra. Agenter inom en fas kan köra parallellt.

Read the full file on GitHub · 137 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. 2mo ago First seen · 137 lines · 1,676 tokens per session scan A 73d887c1b71e

Subscribe to this mod's changes

create-agentic-product CLAUDE.md is an instructions file published in the GitHub repository fltman/create-agentic-product (48 stars, last pushed 9d ago), licensed MIT. It adds 1,676 tokens to every session, about $0.0067 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 2026-08-30.

Building agents
Related

create-agentic-product CLAUDE.md compared with instructions from other repositories

create-agentic-product CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-agentic-product CLAUDE.mdfltman/create-agentic-productInstructions file489d agoMITA1,676Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode