work-brainstorm

work-brainstorm is a skill for Claude Code from christopherlouet/claude-base. It costs 47 tokens per session (1,260 once invoked), scanned A, original, MIT.

A structured brainstorming process for turning a vague software idea into an agreed design before implementation. It uses questions and comparison of possible approaches.

In plain words
What is it for?
Use it to explore an idea, ask focused clarification questions, evaluate alternatives, and prepare for specification and implementation.
Why use it?
It helps uncover the real goal, constraints, users, and success criteria before code is written.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it to explore an idea, ask focused clarification questions, evaluate alternatives, and prepare for specification and implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/christopherlouet/claude-base/work-brainstorm
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 christopherlouet/claude-base --skill work-brainstorm
Clone the repo
git clone --depth 1 https://github.com/christopherlouet/claude-base

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 work-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/christopherlouet/claude-base/work-brainstorm/github.svg)](https://agentmods.dev/skills/christopherlouet/claude-base/work-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/christopherlouet/claude-base/work-brainstorm"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/work-brainstorm/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 work-brainstorm

Your own site · 80×15
<a href="https://agentmods.dev/skills/christopherlouet/claude-base/work-brainstorm"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/work-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,260 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 $0.00047 $0.01260
Opus 5 $0.00023 $0.00630
Sonnet 5 $0.00009 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 6d ago against content hash f56567c5c7a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

work-brainstorm 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 6d 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.

.claude/skills/work-brainstorm/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Brainstorming

Goal

Transform a raw idea into an approved design BEFORE specifying or implementing. Ideation phase between "I have a vague idea" and "here are the user stories".

Vague idea → BRAINSTORM → Validated design → /work:work-specify → /work:work-plan → /dev:dev-tdd

Iron Rule

IMPORTANT: Do NOT invoke an implementation skill, write code, scaffold a project, or take any implementation action until the design has been presented AND approved by the user.

Process

1. Explore the context

Before proposing anything:

  • Read the relevant project files (architecture, existing code, CLAUDE.md)
  • Check recent changes (git log --oneline -10)
  • Identify existing technical constraints
  • Understand the "why" behind the idea

2. Clarify through questioning

Ask clarification questions one at a time (not a block of 10 questions).

Question type Example
Goal "What problem does this solve for the user?"
Scope "Should this work with X or is it independent?"
Constraints "Are there time, budget, or tech limits?"
Users "Who will use this? In what context?"
Success "How will we know it works well?"

Stop questioning when there is enough context to propose alternatives.

3. Propose 2-3 approaches

For each approach, present:

### Approach A: [Descriptive name]

**Principle**: [1-2 sentences]

**Pros**:
- [Pro 1]
- [Pro 2]

**Cons**:
- [Con 1]
- [Con 2]

**Complexity**: [Low / Medium / High]

**Risks**:
- [Risk 1]

4. Challenge the approaches

After presenting the alternatives:

  • Apply YAGNI: "Do we really need X?"
  • Look for the simplest solution that works
  • Identify pieces that can be deferred (P2/P3)
  • Check that a solution does not already exist in the codebase or dependencies

5. Converge on a design

Once the user has chosen a direction:

  • Decompose the system into units with a single clear goal
  • Define the interfaces between units
  • Make sure each unit can be tested independently
  • Present section by section, asking for validation at each step

Read the full file on GitHub · 206 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. 6d ago First seen · 206 lines · 47 tokens per session scan A f56567c5c7a5

Subscribe to this mod's changes

work-brainstorm is a skill published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,260 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 2026-09-03.