intake-project

intake-project is a skill for Claude Code from martian56/claude-engineer. It costs 57 tokens per session (569 once invoked), scanned A, original, MIT.

An interactive project-intake workflow that turns a rough idea or draft into an agreed project brief. It asks questions about users, features, technology choices, and limits before planning begins.

In plain words
What is it for?
Use it to refine an existing draft or interview the requester, then document the problem, users, priorities, technology stack, and non-goals.
Why use it?
It exposes missing requirements and unresolved decisions before coding starts. This helps prevent building the wrong product from an incomplete brief.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-engineer plugin — 13 skills, 1 command, 2 agents, 3 hooks shipped together

Good fit Use it to refine an existing draft or interview the requester, then document the problem, users, priorities, technology stack, and non-goals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martian56/claude-engineer/intake-project
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 martian56/claude-engineer --skill intake-project
Clone the repo
git clone --depth 1 https://github.com/martian56/claude-engineer

Made for: Claude Code.

Or install claude-engineer, the plugin that ships this one along with the rest of its 13 skills, 1 command, 2 agents, 3 hooks.

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 intake-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/martian56/claude-engineer/intake-project.svg)](https://agentmods.dev/skills/martian56/claude-engineer/intake-project)
Your own site
<a href="https://agentmods.dev/skills/martian56/claude-engineer/intake-project"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/intake-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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 $0.00057 $0.00569
Opus 5 $0.00028 $0.00284
Sonnet 5 $0.00011 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 7d ago against content hash b0098192179b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

intake-project 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 7d 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.

plugins/claude-engineer/skills/intake-project/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intake Project

Announce at start: "I'm using claude-engineer:intake-project to pin down what we're building."

Goal: a refined, mutually-agreed brief that the planning stage can turn into a phased plan.

Procedure (create a task per step)

  1. Find the brief. Look for _private/initial-plan-draft.md.
    • Present → read it, then grill the user to fill gaps (see checklist below). Don't accept vagueness.
    • Absent → run an interactive intake interview, then WRITE their answers into _private/initial-plan-draft.md.
  2. Run the requirements/design dialogue via superpowers:brainstorming. Do not skip - it is the discovery engine and the hard gate against premature building.
  3. Resolve the stack decisions that the plan needs (defaults are opinionated; confirm only the genuinely open ones):
    • Frontend: React (Vite SPA) vs Next.js - choose per the project type (see claude-engineer:frontend-development).
    • JS package manager: Bun vs pnpm.
    • Anything project-specific (auth model, external integrations, data shapes).
  4. Capture the brief to _private/initial-plan-draft.md: problem & users, core features (MoSCoW), the agreed stack choices, non-goals, constraints, any reference products/designs, success criteria.
  5. Hand off to claude-engineer:plan-project.

Intake checklist - the brief is not done until these are answered

  • Who are the users and what is the one job-to-be-done?
  • The 3 - 7 core features for v1, and explicit non-goals.
  • React vs Next.js (and why); any second frontend?
  • Design direction / brand / reference products (feeds the DESIGN.md in claude-engineer:design-system).
  • Data model sketch and the key entities.
  • Auth & roles? External services/APIs? Background jobs?
  • Definition of success for v1.

Red flags - STOP and keep grilling

  • "Let's just start coding." → No. Build is plan-gated.
  • Features described as adjectives ("modern", "fast") with no concrete behavior.
  • Stack chosen by habit without matching the project type.
  • The user and you picture different products. Reflect the brief back until it matches.

Read the full file on GitHub · 38 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. 7d ago First seen · 38 lines · 57 tokens per session scan A b0098192179b

Subscribe to this mod's changes

intake-project is a skill published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 569 once invoked, about $0.0003 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.