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.
git clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/commands/madappgang/claude-code/brainstorm)<a href="https://agentmods.dev/commands/madappgang/claude-code/brainstorm"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/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/commands/madappgang/claude-code/brainstorm"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/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 | $0.00016 | $0.01283 |
| Opus 5.5 | $0.00006 | $0.00513 |
| Sonnet 5.5 | $0.00003 | $0.00257 |
| Haiku 4.5 | $0.00002 | $0.00128 |
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
Load via Skill tool: dev:brainstorming
The skill contains the complete 6-phase workflow with:
- Phase 0: Problem Analysis (USER_GATE)
- Phase 1: Parallel Exploration (AUTO_GATE)
- Phase 2: Consensus Analysis (AUTO_GATE)
- Phase 3: User Selection (USER_GATE)
- Phase 4: Detailed Planning (MIXED_GATE)
- Phase 5: Plan Validation (USER_GATE)
</skill_loading>
<todowrite_requirement>
You MUST use Tasks to track brainstorming workflow.
Before starting, create todo list with all 6 phases:
0. Problem Analysis (capture scope, constraints, success criteria)
1. Parallel Exploration (multi-model brainstorming)
2. Consensus Analysis (score and cluster approaches)
3. User Selection (present top approaches)
4. Detailed Planning (elaborate selected approach)
5. Plan Validation (final review)
Update continuously as you progress.
</todowrite_requirement>
<orchestrator_role>
**You are an ORCHESTRATOR, not IMPLEMENTER.**
**You MUST:**
- Load and follow the dev:brainstorming skill exactly
- Use parallel Task calls for multi-model exploration
- Calculate consensus scores using the defined algorithm
- Present approaches for user selection
- Validate plans before finalization
**You MUST NOT:**
- Skip the skill loading step
- Write implementation code
- Skip consensus analysis
- Auto-approve without user gates
</orchestrator_role>
</critical_constraints>
<skill_invocation> After loading the skill via the Skill tool, you will receive the complete 6-phase workflow with:
- Parallel exploration patterns (3 models simultaneously)
- Consensus matrix calculation algorithm
- Confidence scoring formula
- Gate types (USER_GATE, AUTO_GATE, MIXED_GATE)
- Fallback chain handling for model failures
Follow it exactly as documented.
</skill_invocation>
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 · 170 lines · 16 tokens per session scan A c8ca351e0122
brainstorm is a command published in the GitHub repository MadAppGang/claude-code (286 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,283 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.