intake-with-validation

intake-with-validation is a skill for Claude Code from Goktug/ai-crew. It costs 60 tokens per session (3,450 once invoked), scanned A, original, MIT.

A one-question-at-a-time intake process that confirms a user's intent, scope, success criteria, constraints, and exclusions before work begins.

In plain words
What is it for?
Use it at the start of a new team-lead run or when a new requirement appears and must be captured in the project specification.
Why use it?
It reduces mistakes caused by silently guessing what a request means, even when the request seems clear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the ai-crew plugin — 24 skills, 8 commands, 7 agents, 1 hook shipped together

Good fit Use it at the start of a new team-lead run or when a new requirement appears and must be captured in the project specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goktug/ai-crew/intake-with-validation
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 Goktug/ai-crew --skill intake-with-validation
Clone the repo
git clone --depth 1 https://github.com/Goktug/ai-crew

Made for: Claude Code.

Or install ai-crew, the plugin that ships this one along with the rest of its 24 skills, 8 commands, 7 agents, 1 hook.

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-with-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/goktug/ai-crew/intake-with-validation/github.svg)](https://agentmods.dev/skills/goktug/ai-crew/intake-with-validation)
Your own site
<a href="https://agentmods.dev/skills/goktug/ai-crew/intake-with-validation"><img src="https://agentmods.dev/badge/skills/goktug/ai-crew/intake-with-validation/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 intake-with-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/goktug/ai-crew/intake-with-validation"><img src="https://agentmods.dev/badge/skills/goktug/ai-crew/intake-with-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,450 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 $0.00060 $0.03450
Opus 5 $0.00030 $0.01725
Sonnet 5 $0.00012 $0.00690
Haiku 4.5 $0.00006 $0.00345

Measured 9d ago against content hash 213bd22634eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

intake-with-validation 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 9d 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/intake-with-validation/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intake with Validation

Overview

Run structured Q&A one question at a time, even when the request seems crystal clear. The most expensive bugs in a team-lead run come from assumptions the team-lead filled in silently during intake. This skill extracts what the user actually wants — not what they think they should want — and captures scope, success criteria, hard constraints, and non-goals directly in spec.md. No separate intake artifact, no batched questions, no skipping steps because "the user obviously meant X."

When to Use

  • The team-lead is starting Phase 1 (Intake) of a new run.
  • The user invoked /team-lead with any new request — clear, vague, big, or small.
  • A new requirement appeared mid-run that wasn't covered in the original spec.md.

When NOT to use:

  • A pure code-review or read-only investigation that won't write code or open a PR.
  • Continuation of an in-progress run where intake has already happened.

The Process

Step 1 — Hypothesize, with a confidence number

Before asking anything, write down your current best read of what the user actually wants in one sentence, plus an honest confidence number (0–100%). Below ~70%, append a — missing: <what's still unresolved> tail on the same line:

HYPOTHESIS: You want to reduce p99 latency on /pricing by caching responses.
CONFIDENCE: ~25% — missing: actual pain (latency vs. cost vs. rate limit), cache scope, invalidation triggers.
HYPOTHESIS: You want to jitter the midnight cron so it doesn't all fire at 00:00:00.
CONFIDENCE: ~90%

The number forces honesty. If you wrote a high number but can't predict the user's reactions to the next three questions you'd ask (see The 95% confidence stop below), the number is wrong. Start at the confidence level you can defend.

The — missing: tail tells the user exactly what intake needs to surface and prevents the number from being a vague signal.

Step 2 — Ask one question at a time, each with a GUESS attached

Read the full file on GitHub · 266 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. 9d ago First seen · 266 lines · 60 tokens per session scan A 213bd22634eb

Subscribe to this mod's changes

intake-with-validation is a skill published in the GitHub repository Goktug/ai-crew (6 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 3,450 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.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens