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/thepushkarp/brainstorm-plan/brainstormgit clone --depth 1 https://github.com/thepushkarp/brainstorm-planWhat 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 | $0.00892 |
| Opus 5 | $0.00008 | $0.00446 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm: Idea to Design Doc
Help the user turn a fuzzy idea into a fully formed design and specification through structured conversation.
Initial Argument
$ARGUMENTS
Workflow
Step 1: Understand the Context
First, explore the current project state to understand where we're starting:
-
Check if this is an existing project or a new one:
- Look for common project indicators:
package.json,pyproject.toml,Cargo.toml,go.mod,README.md,src/, etc. - If existing project: Use Glob and Read to understand the codebase structure, key files, and existing patterns
- If new/empty project: Acknowledge this and note we're starting fresh
- Look for common project indicators:
-
Briefly summarize what you found (2-3 sentences max) before proceeding to questions.
Step 2: Capture the Initial Idea
If the user provided an argument, use that as the starting idea. Otherwise, ask: "What's the idea you'd like to explore?"
Step 3: Guided Q&A (ONE question at a time)
Ask clarifying questions to refine the idea into a concrete spec:
Rules:
- Ask only ONE question per message
- Prefer multiple choice questions when possible (use AskUserQuestion tool)
- Open-ended questions are OK when choices aren't clear
- Keep questions focused and specific
- Build on previous answers
- Stop when you have enough clarity to write the design
Question areas to cover:
- Core problem being solved
- Target users/use cases
- Key features and behaviors
- Technical constraints or preferences
- Integration with existing code (if applicable)
- Non-goals (what this explicitly won't do)
- Edge cases and error handling
Step 4: Present the Design (in sections)
Once you understand the requirements, describe the design:
Rules:
- Present in sections of 200-300 words each
- After each section, ask: "Does this section look right so far?"
- Wait for confirmation before continuing to the next section
- Revise sections based on feedback before moving on
Suggested design doc structure:
- Overview - What this is and why it matters (1 paragraph)
- Goals - What we're trying to achieve (bullet points)
- Non-Goals - What we're explicitly NOT doing (bullet points)
- User Experience - How users will interact with this
- Technical Approach - High-level architecture and key decisions
- Key Components - Main pieces and how they fit together
- Open Questions - Things still to be decided
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 · 133 lines · 16 tokens per session scan A f2189bcb76a8
brainstorm is a command published in the GitHub repository thepushkarp/brainstorm-plan (11 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 892 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
design
Design-space exploration tree. Wraps /cc-tree:tree with the design preset preselected — enumerates options × trade-offs × reversibility × cost × fit-with-constraints for an engineering / product / process decision. Produces a comparison table and a RECOMMENDED short-list. 中文触发：设计空间探索、方案对比与取舍、给出推荐短名单。.
save
Save this conversation as a new or existing reusable context.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
unslop
Cut AI tells from any writing. Must always apply.