mastermind-intake

Mastermind Intake Protocol

This file is referenced by master.md and domain commands. Never invoke directly.

---

Rich Prompt Detection

Count the words in $ARGUMENTS and scan for domain signals.

Rich prompt (skip all intake questions → proceed to execution) if EITHER of these holds:

• A. Long + domain-signaled: word count ≥ 20 AND contains at least one domain signal (build, ship, feature, bug, fix, campaign, marketing, SEO, content, review, audit, research, launch, release, sales, outreach, ops, finance, report).
• B. Concrete imperative: contains a clear imperative verb (fix, add, remove, rename, update, refactor, migrate, upgrade, revert, patch, bump) AND names something specific enough that no reasonable person would need clarifying questions — a file/path, a function/class/component name, an error message or stack-trace fragment, a bug symptom with a concrete detail (a number, duration, status code, version), or a named third-party service/library. This counts as rich even under 20 words and without a goal/outcome phrase. Examples:
  • "Fix the login bug where sessions expire after 5 minutes instead of 30"
  • "Rename getUserData to fetchUserProfile in src/api/users.ts"
  • "Update the Stripe webhook handler to retry on 502s"
  • "Remove the unused legacyAuth middleware"

Vague prompt (run intake): anything that meets neither A nor B.

Even with a rich prompt, if --confirm flag is present: skip to execution but show the plan before spawning agents and wait for "go".

---

Intake Questions

Ask ONE question at a time. Wait for the answer before asking the next. Stop asking as soon as you have enough to proceed.

Q1 — Goal:

"What outcome defines success for this run? Be as specific as you can — what will be done or produced when we're finished? (Or just say 'you decide' at any point and I'll infer the rest.)"

Q2 — Scope:

Infer the likely domain(s) from the Q1 answer using this keyword mapping (case-insensitive substring match; a "don't over-engineer" heuristic, not a classifier):