brainstorming-a-feature

brainstorming-a-feature is a skill for Claude Code from redhuntlabs/wizard. It costs 31 tokens per session (1,066 once invoked), scanned A, original, MIT.

A feature-scoping workflow that turns a rough idea into a problem statement, possible approaches, trade-offs, and a recommendation with an alternative considered.

In plain words
What is it for?
Use it when starting a feature, preparing an implementation plan, resolving disagreement about the design, or clarifying who the feature serves and what problem it solves.
Why use it?
It makes an unclear feature request specific before implementation begins. It also records the user, constraints, and reasons for choosing one approach over others.

Skill for Claude Code

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

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Use it when starting a feature, preparing an implementation plan, resolving disagreement…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/brainstorming-a-feature
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 redhuntlabs/wizard --skill brainstorming-a-feature
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 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 brainstorming-a-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/brainstorming-a-feature.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/brainstorming-a-feature)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/brainstorming-a-feature"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/brainstorming-a-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 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 $0.00031 $0.01066
Opus 5 $0.00015 $0.00533
Sonnet 5 $0.00006 $0.00213
Haiku 4.5 $0.00003 $0.00107

Measured 7d ago against content hash 58841e2082d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

brainstorming-a-feature 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.

spells/dev/brainstorming-a-feature/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorming a Feature

What this does

Turns a feature idea into a structured brainstorm: a sharp problem statement, the user it serves, the constraints that bound the solution, 3-5 candidate approaches with trade-offs, and a recommendation with an explicit alternative considered.

When to use

  • Starting work on a new feature
  • Before writing an implementation plan
  • When the team disagrees on approach
  • When the feature feels mushy and needs sharpening

What you bring (Inputs)

  • A one-line description of the feature ("we want to add X")
  • The user (which user; what role; what they're trying to do)
  • Known constraints (timeline, tech, dependencies, regulatory)

What you get (Output)

A brainstorm document: problem statement, user, constraints, 3-5 candidate approaches with trade-offs, recommendation, and the alternative considered.

How it works (Steps)

This is a workflow.

Stages

Stage 1: Sharpen the problem

Write the problem in one sentence. Format: "[User] needs to [do X] but [obstacle], which causes [pain]."

If you cannot complete that sentence, the problem isn't sharp enough yet. Interview a real user or revisit the source request.

Stage 2: Name the user

Specifically. Not "users." Which segment, which role, which context. If multiple — pick the primary one for v1.

Stage 3: Enumerate constraints

What MUST be true of any solution? Examples:

  • Ships in Q2
  • No new infra
  • Backwards compatible with API v1
  • Doesn't increase p95 latency

Constraints are not preferences — they're hard limits.

Stage 4: Generate 3-5 candidate approaches

For each: 1-3 sentences describing what it is, what it requires, what it costs, what it forecloses.

If you can only think of one, you haven't brainstormed. Force at least 3, even if some are obviously bad — bad approaches sharpen the good ones.

Stage 5: Score and recommend

For each approach against criteria like: time-to-ship, risk, fit with existing system, user experience, future flexibility. Pick a winner.

Read the full file on GitHub · 121 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 · 121 lines · 31 tokens per session scan A 58841e2082d0

Subscribe to this mod's changes

brainstorming-a-feature is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,066 once invoked, about $0.0002 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.