product-intent

product-intent is a skill for Claude Code, Codex from JakubMikolajek/codex-skills-collection. It costs 76 tokens per session (1,630 once invoked), scanned A, original, MIT.

A process for connecting a software feature to the user or business outcome it is meant to achieve. It turns requirements into measurable acceptance checks and compares the finished work with that intent.

In plain words
What is it for?
Use it when a feature's users or success conditions are unclear, when planning a user-facing flow, or when checking whether an implementation meets its stated purpose.
Why use it?
It helps prevent teams from building something technically complete that does not solve the intended problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it when a feature's users or success conditions are unclear, when planning a user-facing flow, or when checking whether an implementation meets its stated purpose.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jakubmikolajek/codex-skills-collection/product-intent
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 JakubMikolajek/codex-skills-collection --skill product-intent
Clone the repo
git clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collection

Made for: Claude Code, Codex.

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-intent

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/product-intent/github.svg)](https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/product-intent)
Your own site
<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/product-intent"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/product-intent/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-intent

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/product-intent"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/product-intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,630 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 $0.00076 $0.01630
Opus 5 $0.00038 $0.00815
Sonnet 5 $0.00015 $0.00326
Haiku 4.5 $0.00008 $0.00163

Measured 12d ago against content hash 5d5c39585750, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

product-intent 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.

skills/product-intent/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Intent

This skill bridges business requirements and technical implementation. It ensures the team is building the right thing before building it well, and verifies the right thing was actually delivered after.

When to Use

  • User describes a feature without stating a clear user goal or success condition
  • Task involves a new user-facing flow, screen, or interaction
  • Implementation plan exists but no one has asked "why does this matter to the user?"
  • After implementation to verify the shipped code actually satisfies the stated user need
  • When implementation-gap-analysis signals technical completeness but the feature still feels wrong
  • Before task-analysis or architecture-design when the feature scope is ambiguous
  • When a stakeholder or ticket describes what to build but not for whom or why

When NOT to Use

  • Task is purely infrastructure, refactoring, or developer tooling with no end-user surface
  • Product intent is already clearly documented and agreed upon in a PRD or ticket — skip directly to task-analysis
  • Task is a bug fix with a clear reproduction — bug fixes restore existing intent, not establish new intent
  • User explicitly says "I know what I want, help me build it"

Core Principles

Intent Before Architecture

Do not let technical decisions precede intent clarity. A perfectly architected system that solves the wrong problem is a failure. Run this skill before architecture-design and task-analysis when the user goal is not explicit.

Measurable Success Criteria

Vague acceptance criteria ("user can see their data") are useless for verification. Every success criterion must be concrete enough to pass or fail a manual or automated test.

Bad: "User can manage their documents" Good: "User can upload a document ≤10MB, see it listed within 2 seconds, and delete it — with the deletion reflected immediately in the list"

Anti-Goals Are First-Class

Stating what a feature explicitly does NOT do is as valuable as stating what it does. Anti-goals prevent scope creep, keep the implementation focused, and give agents a basis for declining out-of-scope requests.

Read the full file on GitHub · 172 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 · 172 lines · 76 tokens per session scan A 5d5c39585750

Subscribe to this mod's changes

product-intent is a skill published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 1,630 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens