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/sjarmak/coding-agent-workflows/brainstormnpx skills add sjarmak/coding-agent-workflows --skill brainstormgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWhat 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 | $0.00067 | $0.01470 |
| Opus 5 | $0.00034 | $0.00735 |
| Sonnet 5 | $0.00013 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm: Constrained Divergence
You are facilitating a structured brainstorming session.
Core principle: creativity is non-standard problem solving. The first idea is almost never the best. To find the best idea you have to push far past the obvious, and the only way to do that is volume under a hard no-repetition constraint.
Arguments
[count] "problem statement"
- A leading integer sets the idea target (default 30).
- The rest is the problem to explore.
- No problem given: ask the user what to brainstorm.
The one rule: shape uniqueness
Every new idea must differ in shape from:
- Every piece of prior art cataloged during research (known approaches).
- Every earlier idea in this session.
"Shape" is the structural approach, not surface details. Renaming, re-skinning, or tweaking parameters does not make a new idea: if you could describe two ideas with the same diagram, they are the same shape.
Enforcing this is a judgment, not a string match, so it is your job, not a script's: before recording an idea, compare its structure against the prior-art list and every earlier idea. If it collapses onto one of them, reject it and go somewhere genuinely different. This is the ZFC split the bundle applies everywhere: shape-uniqueness is semantic classification, which the model does and a regex cannot.
Tracking state (no backend required)
Keep the session in one markdown file, .brainstorm/<slug>.md in the working
directory, so it survives across turns and can be resumed:
- Prior art — the structurally distinct known approaches (title, one-line why-it-works, source).
- Ideas — numbered, each with a title, a one-line shape description, and (after the prototype gate) a note or link to its MVP.
- Ratings — once converging, Feasibility / Novelty / Impact per idea.
That file is the whole store. No database, no external CLI.
Rules of engagement
- No premature judgment. During divergence, never dismiss, critique, or filter. Every idea gets recorded. "That won't work" is banned until converge.
- Volume before quality. Most ideas will be bad. That is the point.
- Enforce the shape gate honestly. You are both proposer and gate; do not wave through a reskin because it is yours. When an idea repeats a shape, push further.
- Separate diverge from converge. Evaluate only after all ideas are captured.
- Be a partner, not a scribe. Offer ideas, riff, keep the energy up.
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.
- 2d ago First seen · 142 lines · 67 tokens per session scan A 26ed7ff33df9
brainstorm is a skill published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,470 once invoked, about $0.0003 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
huashu-design
花叔Design——用HTML做高保真原型、幻灯片、动画、可视化与专家评审。任何新设计100%先出三个方向初稿给用户选（指定风格/品牌也不豁免），选定后才执行。触发词：做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web App/需后端的系统不适用。.
muapi-ai-clipping
Turn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's /ai-clipping endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe…
muapi-youtube-shorts
Auto-generate viral 9:16 YouTube Shorts (or TikTok / Reels clips) from a long-form video. Thin platform-aware wrapper around the AI Clipping skill — picks sensible defaults for short-form social platforms (9:16, 30–60s sweet spot) and delegates the actual highlight extraction + crop to muapi.ai's /ai-clipping endpoint.
muapi-cinema-director
Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai.
muapi-nano-banana
Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting.
data-artist
Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.