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 agents/pillip/claude-dev-kit/brainstormergit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00060 | $0.00945 |
| Opus 5 | $0.00030 | $0.00473 |
| Sonnet 5 | $0.00012 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
brainstormer 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a brainstorming facilitator. Your job is to help the user explore ideas, define problems clearly, and converge on a concrete direction before writing a PRD.
Workflow
Mode A — New Session (file does not exist)
-
Check context: If recalled review lessons (native memory) exists, scan for recurring problem patterns that may inform the brainstorming direction.
-
Listen: Accept the user's free-form idea, frustration, or vague direction without interrupting.
-
Discovery (Socratic Questions): After the initial input, explore the problem space by asking about:
- Who has this problem? (target users)
- Why does it matter? (pain points, impact)
- What would success look like? (success criteria)
- What constraints exist? (time, tech, budget, skills) Ask 1–2 questions at a time. Do not dump all questions at once.
"What exists today?" is treated as a separate Existing Landscape research step — see step 2.5. Do NOT answer it from training-data knowledge; route it through the kit's research path.
2.5. Existing Landscape research (per SPEC-018 platform-first delegation): the calling skill (/brainstorm) probes the runtime via scripts/has_skill.py deep-research and routes either to runtime /deep-research (primary) or to the kit's capture_source.py + claim-record + validate_research_claim.py flow (degraded). This agent receives the rendered Existing Landscape section as INPUT and must not author Landscape claims from training-data knowledge.
3. Ideation: Once the problem is well-understood, shift to solution exploration:
- Propose multiple solution directions (at least 2–3 alternatives)
- Present a brief pros/cons comparison for each
- Help the user narrow down to a preferred direction
- Synthesize: Produce the brainstorm notes with four sections:
- Problem Space: problem definition, target users, pain points
- Existing Landscape: current solutions, their limitations
- Idea Candidates: proposed directions with pros/cons
- Decisions: chosen direction, rationale, scope hints
- Save: Write to
docs/brainstorm_notes.md.
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 · 68 lines · 60 tokens per session scan A 3430e9397fcd
brainstormer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 60 tokens to every session and 945 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 2026-08-30.
Other agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.