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 commands/luanmorenommaciel/agentspec/brainstormgit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWrote 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/luanmorenommaciel/agentspec/brainstorm)<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/brainstorm"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/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 | $0.00016 | $0.00505 |
| Opus 5 | $0.00008 | $0.00253 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
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.
What it actually says
Brainstorm Command
Phase 0 of the SDD workflow — optional, and the only phase that starts from nothing but an idea. Its output feeds
/define(Phase 1).
Usage
/brainstorm <idea-or-request>
/brainstorm "Build a real-time notification system"
/brainstorm notes/rough-idea.txt
Arguments: a quoted idea, problem statement, or feature request — or a path to a file containing rough notes.
Examples
# From a direct idea
/brainstorm "I want to automate data quality checks"
# From a file with notes
/brainstorm docs/meeting-notes.md
# From a problem statement
/brainstorm "Our team spends too much time on manual data entry"
What happens
- Load
.claude/skills/sdd-brainstorm/SKILL.mdand follow it — the skill owns the methodology: KB-first grounding, one-question-at-a-time discovery, sample collection, 2-3 approach comparison, YAGNI, incremental validation, and the quality gate. - Produce the BRAINSTORM artifact at
.claude/sdd/features/BRAINSTORM_{FEATURE}.md, shaped by.claude/sdd/templates/BRAINSTORM_TEMPLATE.md. - Suggest the next step:
/define .claude/sdd/features/BRAINSTORM_{FEATURE}.md.
When to use /brainstorm vs /define
| Scenario | Use |
|---|---|
| Vague idea, need to explore | /brainstorm |
| Clear requirements, ready to capture | /define directly |
| Existing BRAINSTORM document | /define <brainstorm-file> |
| Meeting notes with clear asks | /define directly |
| "I want to build something but not sure what" | /brainstorm |
References
- Skill (methodology):
.claude/skills/sdd-brainstorm/SKILL.md - Agent (executor):
.claude/agents/workflow/brainstorm-agent.md - Template (artifact shape):
.claude/sdd/templates/BRAINSTORM_TEMPLATE.md - Contracts (phase obligations):
.claude/sdd/architecture/WORKFLOW_CONTRACTS.yaml - Next phase:
.claude/commands/workflow/define.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 · 56 lines · 16 tokens per session scan A 86a42f766acc
brainstorm is a command published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 505 once invoked, about $0.0001 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.