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.
npx agentmods add skills/yunsii/wezdeck/brainstormnpx skills add yunsii/wezdeck --skill brainstormgit clone --depth 1 https://github.com/yunsii/wezdeckWrote 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.
[](https://agentmods.dev/skills/yunsii/wezdeck/brainstorm)<a href="https://agentmods.dev/skills/yunsii/wezdeck/brainstorm"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/brainstorm.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00100 | $0.01667 |
| Opus 5 | $0.00050 | $0.00834 |
| Sonnet 5 | $0.00020 | $0.00333 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm (platform skill — single source)
Who runs: the coding agent, not the human.
Never tell the user to copy-paste run.sh as the primary path.
Never replace this with a solo idea dump and call it a brainstorm — the
point is multiple independent personas + cross-model, then a judge.
This directory is the only skill + runner unit. Other paths are symlinks
(installed by scripts/dev/link-platform-skills.sh). Do not maintain a second
SKILL.md body.
Who runs what
| Actor | Duty |
|---|---|
| Human | Intent only:「头脑风暴」「帮我想想点子」「发散一下这个问题」 |
| Any agent | Load this skill → phrase the problem → run → relay result |
| Host headless backends | claude / codex / grok as personas / challenger / judge |
When to load / run
- User wants ideas, options, approaches, or angles on an open-ended question
- User explicitly says 头脑风暴 / brainstorm / 发散 / 想点子
Skip / redirect:
- Concrete diff / existing code → adversarial-review (this skill is generative, not a defect finder)
- Someone's design doc / RFC / ADR / 方案 when the intent is only to
evaluate that proposal → default 设计评审 (main-agent structured
challenge; host
validation.md→ Design proposal review). Do not default to a full diverge pass that ignores the proposal - Same design doc when the user still wants alternatives → this skill is appropriate: phrase problem + extract hard constraints from the doc; prefer challenge-heavy use; full diverge only if the problem space is still open
Three stages (divergent → convergent)
| Stage | Role | Stance |
|---|---|---|
| 1 diverge | N persona lenses × cross-provider | expand — maximize novelty, no self-censoring |
| 2 challenge | devil's advocate | stress-test feasibility/risk, do not delete ideas |
| 3 converge | judge / facilitator | blind-rank + synthesize a recommendation |
Built-in personas (lenses): Moonshot Innovator · Pragmatic Builder ·
End-User Advocate · Contrarian/First-Principles. Configurable in
lib/personas.conf — add a lens = one line, no code edits.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 150 lines · 100 tokens per session scan A dd8a09e4f71a
brainstorm is a skill published in the GitHub repository yunsii/wezdeck (5 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 1,667 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 2026-08-31.
Other skills, from other repositories
workflow
Create, run, monitor, cancel, or resume deterministic JavaScript workflows that orchestrate multiple Codex, Claude, Cursor, or Kimi agents. Use for parallel investigation or review, staged agent pipelines, resumable long-running work, or when the user explicitly asks for a workflow, orchestration, fan-out, or several…
orchestrate
Use only when the user explicitly types /orchestrate:orchestrate to decompose a large task, spawn a tree of parallel worker/subplanner/verifier subagents, and collect structured handoffs. Do not invoke autonomously.
launch
Launch and automate VS Code (Code OSS) using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test UI features, or take screenshots of VS Code. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch…
accessibility
Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
sessions
Agent Sessions window architecture — covers the sessions-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agent Sessions window.
component-fixtures
Use when creating or updating component fixtures for screenshot testing, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, and common pitfalls.