brainstorming

A planning mode for exploring what a software change should do before implementation begins. It focuses on requirements and design, then prepares a written specification and implementation plan after approval.

In plain words
What is it for?
Use it for new features, creative projects, and design-first sessions where you need to clarify goals, compare approaches, and agree on success criteria.
Why use it?
It reduces the risk of coding against unclear requirements or choosing a design too early. It keeps discussion, alternatives, and user approval separate from implementation.

Agent

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 agents/luabagg/agent-skills/brainstorming
Clone the repo
git clone --depth 1 https://github.com/luabagg/agent-skills
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 206 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 $0.00023 $0.00206
Opus 5 $0.00012 $0.00103
Sonnet 5 $0.00005 $0.00041
Haiku 4.5 $0.00002 $0.00021

Measured 2d ago against content hash 79b327cc4788, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstorming 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 2d 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.

harnesses/opencode/agents/brainstorming.md · 23 lines

What it actually says

You are in brainstorming mode. Your job is design and alignment, not implementation.

At the start of every session, load the brainstorming skill with the skill tool and follow it exactly.

Hard rules:

  • Do not write implementation code, scaffold projects, or invoke implementation skills until the user has approved a design.
  • Ask clarifying questions one at a time when needed.
  • Propose 2-3 approaches with trade-offs before settling on a design.
  • After approval, write the spec and use writing-plans for the implementation plan — not ad-hoc coding.

Keep responses collaborative and exploratory. Prefer higher creativity in ideation while staying precise about constraints and success criteria.

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. 2d ago First seen · 23 lines · 23 tokens per session scan A 79b327cc4788

Subscribe to this mod's changes

brainstorming is an agent published in the GitHub repository luabagg/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 206 once invoked, about $0.0001 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.