conversation-intake

conversation-intake is a skill for Claude Code from PMDevSolutions/Aurelius. It costs 98 tokens per session (2,779 once invoked), scanned A, original, MIT.

A structured interview workflow that turns a plain-language app idea into a build specification and a design brief. It asks targeted questions and records decisions so later design and coding steps do not need to repeat the discussion.

In plain words
What is it for?
Gathering app requirements, discovering local project context, and producing build-spec.json and design-brief.json for a later design-and-build workflow.
Why use it?
It gives a vague product idea a clear, machine-readable starting point when there is no Figma file, screenshot, or URL. This reduces missing requirements and repeated clarification.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - Run: node scripts/renderer-registry.js detect . --json.

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/PMDevSolutions/Aurelius
agentmods
npx agentmods add skills/pmdevsolutions/aurelius/conversation-intake

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 conversation-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/conversation-intake.svg)](https://agentmods.dev/skills/pmdevsolutions/aurelius/conversation-intake)
Your own site
<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/conversation-intake"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/conversation-intake.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00098 $0.02779
Opus 5 $0.00049 $0.01389
Sonnet 5 $0.00020 $0.00556
Haiku 4.5 $0.00010 $0.00278

Measured yesterday against content hash a2179eba66f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

conversation-intake 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 yesterday.

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/skills/conversation-intake/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Intake — Structured Discovery

Purpose

Gather everything needed to design and build an app from nothing but a conversation. Where figma-intake discovers an existing design file, this skill discovers the user's intent: it interviews them (maximum of 7 questions), expands the answers into concrete design decisions via the conversation-designer agent, and outputs two machine-readable artifacts that the rest of the pipeline consumes without re-asking questions:

  • .claude/plans/build-spec.json with "source": "conversation" — same contract every other intake skill produces
  • .claude/plans/design-brief.json — the new artifact that drives Figma design generation in Phase C1

When to Use

  • Phase C0 of /build-from-conversation
  • Any time a user describes an app they want built but has no Figma/Canva file, screenshot, or URL
  • When you need a structured design brief from a free-form product description

Inputs

  • Optional: Initial description from $ARGUMENTS (seed answers; skip any question it already answers)
  • Optional: Existing project directory to integrate into
  • Reads: .claude/pipeline.config.jsonconversation.interview (maxQuestions, confirmBriefWithUser)

Process

Step 1: Auto-Discovery (No User Input)

Scan the local project exactly as the other intake skills do:

1. Detect framework via the renderer registry:
   - Run: node scripts/renderer-registry.js detect . --json
   - On { "renderer": "<name>", "language": "<lang>" }:
       set build-spec renderer = <name>
       set build-spec outputTarget = <language>  (react | vue | svelte | react-native)
   - On { "renderer": null }:
       no framework detected → ask the output-target question (Question 5)
   Do not hand-sniff config files or package.json deps; the registry owns detection.

2. Detect app type:
   - manifest.json with "manifest_version" → Chrome Extension
   - manifest.json with "start_url" or "display" → PWA
   - Otherwise → Web App

3. Scan existing components:
   - Glob: src/components/**/*.tsx, app/components/**/*.tsx
   - Build inventory: name, props interface, file path
   - (Only triggers Question 7 if matches exist)

4. Check package.json for UI libraries and state management
   (same list as figma-intake)

5. Check for existing design tokens:
   - tailwind.config.ts theme.extend, src/styles/tokens.css,
     design-tokens.lock.json (from prior runs)
   - Existing tokens become constraints for the design brief, not questions

6. Load pipeline config:
   - .claude/pipeline.config.json → conversation.interview.maxQuestions (default 7)
     and appTypes[detected] for E2E strategy defaults

Read the full file on GitHub · 232 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. yesterday First seen · 232 lines · 0 tokens per session scan A a2179eba66f2

Subscribe to this mod's changes

conversation-intake is a skill published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 98 tokens to every session and 2,779 once invoked, about $0.0005 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 2026-09-04.