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/agent-workflows/brainstormnpx skills add sjarmak/agent-workflows --skill brainstormgit clone --depth 1 https://github.com/sjarmak/agent-workflowsWrote 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/sjarmak/agent-workflows/brainstorm)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/brainstorm"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/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 | $0.00064 | $0.01980 |
| Opus 5 | $0.00032 | $0.00990 |
| Sonnet 5 | $0.00013 | $0.00396 |
| Haiku 4.5 | $0.00006 | $0.00198 |
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 — 190 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 idea. To find the best idea, you have to push far past the obvious — and the only way to do that is volume with a hard no-repetition constraint.
Parsing Arguments
$ARGUMENTS may start with a number (the idea target). Parse it:
/brainstorm 10 How to optimize our API→ target=10, problem="How to optimize our API"/brainstorm How to optimize our API→ target=30 (default), problem="How to optimize our API"
Pass to init: python3 ${CLAUDE_SKILL_DIR}/scripts/brainstorm.py init "<problem>" --count <N>
The One Rule
Every new idea must differ in shape from:
- Every piece of prior art cataloged during research (existing known approaches)
- Every previous idea in this session
"Shape" means 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.
The add command enforces this mechanically. When rejected, just go somewhere
genuinely different.
Rules of Engagement
- No premature judgment. During divergence, NEVER dismiss, critique, or filter ideas. Every idea gets recorded. "That won't work" is banned until convergence.
- Volume before quality. Most ideas will be bad. That's the point.
- Trust the gate. The
addcommand enforces shape uniqueness. Just propose and submit — the system handles detection. When rejected, go further. - Separate diverge from converge. Only evaluate after all ideas are captured.
- Collaborative, not passive. You are a brainstorming partner. Offer ideas, riff, keep the energy up.
Tools
All session management goes through the brainstorm CLI:
python3 ${CLAUDE_SKILL_DIR}/scripts/brainstorm.py <command> [args]
Commands:
init "<problem>" [--count N]— Start a new session (default: 30 ideas)prior-art <session> "<title>" ["<desc>"] [--source S]— Record a known approach (banned)prior-art-list <session>— List all cataloged prior artbegin <session>— Transition from research to divergenceadd <session> "<title>" ["<description>"]— Record an ideaupdate <session> <num> [--title T] [--desc D] [--status S] [--notes N]— Update an idearate <session> <num> <feasibility> <novelty> <impact>— Rate (1-5 each)check-code <session> <idea-number>— Check prototype code uniquenessstatus <session>— Progress dashboardlist <session>— List all ideasphase <session>— Progress check + exclusion zone summaryreport <session>— Generate convergence reportsessions— List all sessions
What ships with it
4 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 · 190 lines · 0 tokens per session scan A b7c27d2a5c0b
brainstorm is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,980 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
speckit.specify
Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.
speckit.clarify
Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.
local-integration-testing
Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.
release-docs
Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…
update-docs
Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…
docker-compose-first-install
Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.