spec-brainstorm

spec-brainstorm is a skill for Claude Code from martinffx/atelier. It costs 95 tokens per session (3,131 once invoked), scanned A, original, MIT.

A conversational workshop for turning a substantial software idea into a reviewed design document. It asks one question at a time, compares possible approaches, and waits for approval before writing the design.

In plain words
What is it for?
Use it to explore requirements, research the codebase, compare architecture options, control scope, and produce a design.md file for a larger change.
Why use it?
It helps uncover missing requirements and settle important design choices before implementation begins. It also keeps the work limited to the approved design document.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions AGENTS.md.

Part of the atelier plugin — 14 skills shipped together

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.

agentmods
npx agentmods add skills/martinffx/atelier/spec-brainstorm
Any agent
npx skills add martinffx/atelier --skill spec-brainstorm
Clone the repo
git clone --depth 1 https://github.com/martinffx/atelier

Made for: Claude Code.

Or install atelier, the plugin that ships this one along with the rest of its 14 skills.

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 spec-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/martinffx/atelier/spec-brainstorm.svg)](https://agentmods.dev/skills/martinffx/atelier/spec-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/martinffx/atelier/spec-brainstorm"><img src="https://agentmods.dev/badge/skills/martinffx/atelier/spec-brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,131 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 $0.00095 $0.03131
Opus 5 $0.00048 $0.01566
Sonnet 5 $0.00019 $0.00626
Haiku 4.5 $0.00010 $0.00313

Measured 6d ago against content hash d17b2f7654b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-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.

skills/spec-brainstorm/SKILL.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Brainstorm

Conversational design workshop for substantial work that produces a focused, reviewed spec.

One question at a time. Multiple approaches explored. Design approved in sections. Ruthless scope control. No implementation until design is approved.

Run this skill only after atelier-orchestrator selects a Spec-backed Plan or the human explicitly requests a spec. Bounded work should go directly to spec-plan for an Inline Plan. Do not reclassify the planning mode here.

Artifact

docs/specs/YYYY-MM-DD-<feature>/
└── design.md  ← This skill's output

Requirements are inline — no separate requirements.json needed.

Exclusive output contract

This skill may create or update only the design.md shown above. It may inspect the repository and discuss drafts in conversation, but it must not modify any other file, create plan.json, create tracker entries, invoke another workflow skill, or write implementation code. This boundary still applies when the human asks to brainstorm, plan, and implement in one request. Finish design.md, report it, and stop.


Lessons

These principles apply to every spec, every time.

Specs must earn their cost

Persisted specs are for work whose discovery, architecture, dependencies, or coordination needs justify a durable artifact. Do not pull bounded work into this workflow merely because it touches multiple files or takes time. That work belongs in an Inline Plan.

Design for isolation and clarity

Break the system into units with one clear purpose each. Well-defined interfaces between them. Each unit independently understandable and independently testable. If you can't explain a unit's job in one sentence, it's doing too much.

Working in existing codebases

Explore the current structure first. Follow existing patterns. Targeted improvements only. No unrelated refactoring. Understand why things are the way they are before proposing changes. Treat loaded skills as relevant guidance, not as a requirement to apply every pattern they contain.

Read the full file on GitHub · 385 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 · 385 lines · 95 tokens per session scan A d17b2f7654b2

Subscribe to this mod's changes

spec-brainstorm is a skill published in the GitHub repository martinffx/atelier (45 stars, last pushed 27d ago), licensed MIT. It adds 95 tokens to every session and 3,131 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 2026-08-30.

Related

Other skills, from other repositories

lingui-best-practices

Implement internationalization with Lingui in React and JavaScript applications. Use when adding i18n, translating UI, working with Trans/useLingui/Plural, extracting messages, compiling catalogs, or when the user mentions Lingui, internationalization, i18n, translations, locales, message extraction, ICU…

lingui/skills · 78 tokens

enhanced-message-context

Add translator comments to Lingui messages so translations are accurate. Use when adding or modifying translatable messages, when strings are short or ambiguous ("Back", "Delete", "Post"), when placeholders are unclear ({count}, {name}), when deciding between comment and context, or when auditing extracted .po…

lingui/skills · 70 tokens

migrate-i18next-to-lingui

Migrate i18next/react-i18next projects to Lingui. Use when the user wants to replace i18next, react-i18next, useTranslation, i18n.t(), Trans i18nKey, or i18next JSON catalogs with Lingui equivalents. Covers package installation, config setup, code transformation patterns, plural migration, namespace handling, and…

lingui/skills · 86 tokens

brainstorm

Explore the solution space when the path isn't obvious - invent options, stress-test them, pick one. Use for architecture decisions, design tradeoffs, and when the user asks 'how should I approach X?'. Default produces a decision brief; pass --quick for chat-only, --deep for multi-round adversarial debate with full…

vanducng/skills · 125 tokens

worktree

Create, inspect, and clean isolated git worktrees for parallel feature development. Standardizes worktrees under a top-level .worktrees/ dir, auto-copies .env files (nested included), assigns each worktree a deterministic port block, trusts mise configs in the new worktree when present, and runs lifecycle hooks for DB…

vanducng/skills · 134 tokens

find-unwrapped-strings

Audit a Lingui project for hardcoded user-facing strings that were never wrapped in macros. Use when asked to find untranslated, unwrapped, or hardcoded strings, to check i18n coverage, to audit what an i18n setup or migration missed, or when text renders in the source language after everything was supposedly…

lingui/skills · 72 tokens