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 skills add momentmaker/kaijutsu --skill brainstormgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/momentmaker/kaijutsu/brainstorm)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/brainstorm"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/brainstorm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/brainstorm"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00137 | $0.01216 |
| Opus 5.5 | $0.00055 | $0.00486 |
| Sonnet 5.5 | $0.00027 | $0.00243 |
| Haiku 4.5 | $0.00014 | $0.00122 |
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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brainstorm
Three reviewers walk into a question. Each comes back with a different list. The synthesizer ranks them.
This skill wraps jutsu swarm brainstorm. Free-form prompt input, ranked-list output. Use it before decide (you don't know what to record yet) or before refactor-plan (you don't know which approach to plan against yet).
How agents collaborate
| Lens | Agent | Looks for |
|---|---|---|
| Long-horizon framing | claude | Ideal end-state, ambition gap, bold-but-defensible moves |
| Code-pattern grounding | codex | Existing patterns, concrete libraries, real-world failure modes |
| Cross-domain analogy | antigravity | Adjacent fields, prior art, RFC/paper precedents |
Severity vocab differs from pr-review/doc-review. Brainstorm options use:
- recommended — high-confidence "this is what I'd do"
- alternative — also good, different tradeoff profile
- risky — works but with caveats
- speculative — wild idea worth recording, not yet defensible
The synthesizer ranks options across reviewers, groups similar approaches, and surfaces "cross-cuts" — themes that appeared in multiple options.
Layout (rich)
brainstorm/
├── SKILL.md
├── skill.yaml
├── scripts/
│ └── run.sh
├── prompts/
│ ├── claude.md long-horizon lens
│ ├── codex.md code-pattern lens
│ ├── antigravity.md cross-domain lens
│ ├── synthesizer.md ranked-list assembler
│ └── debate.md Pass-2 critique template
└── references/
├── lens-design.md why each lens is what it is
└── chaining.md how brainstorm composes with decide / refactor-plan
First-run consent
Brainstorm sends the user prompt to remote model providers. Per-repo consent required before the first run:
jutsu swarm brainstorm --grant-consent
This writes allow-multi-model: true to .kaijutsu/brainstorm.yaml. Subsequent runs work non-interactively.
When to invoke
# Direct
jutsu swarm brainstorm "how do I rate-limit my API endpoints?"
# Via skill wrapper
~/.claude/skills/brainstorm/scripts/run.sh "what's the right cache invalidation strategy?"
# High-stakes question — use --full for a debate round
jutsu swarm brainstorm "should we migrate from Postgres to CockroachDB?" --full --strict
# Iterate cheap on the synth prompt
jutsu swarm brainstorm --replay <key>
What ships with it
9 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.
- 1mo ago First seen · 121 lines · 137 tokens per session scan A fe4a09b37279
brainstorm is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 8d ago), licensed MIT. It adds 137 tokens to every session and 1,216 once invoked, about $0.0005 per session on Opus 5.5. 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.