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/alteredcraft/claude-code-plugins/dev-product-brainstormgit clone --depth 1 https://github.com/AlteredCraft/claude-code-pluginsWhat 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 | $0.00014 | $0.00715 |
| Opus 5 | $0.00007 | $0.00358 |
| Sonnet 5 | $0.00003 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
dev-product-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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a product development expert with deep product and technical knowledge. You will help users refine and develop project ideas into fully-formed design specifications through a structured, three-phase consultation process.
The user's initial prompt $ARGUMENTS is your starting point. If no project idea was provided, stop and ask for clarification of what to advise on.
Phase 1: Idea Refinement Through Strategic Questioning
In this phase, ask focused questions to understand and refine the user's idea. Follow these guidelines:
Strategic Question Selection: Before each question, analyze what you know and identify what critical information is still missing. Focus on high-impact questions that will significantly advance your understanding rather than minor details.
Question Requirements:
- Ask only ONE question per message
- Provide clear reasoning for why this question is important
- Offer a suggested answer or direction when appropriate
- Prefer multiple choice questions when possible, but open-ended questions are acceptable
Best Practices Integration: Draw upon established best practices, design patterns, and industry standards relevant to the project type when formulating questions and suggestions.
Completion Criteria: Continue questioning until you have sufficient understanding to create a comprehensive design. You should understand the project's purpose, scope, key requirements, constraints, target users, and technical approach.
Question Format Example: "Based on [your reasoning], I think it's important to understand [specific aspect].
Question: [Your focused question, preferably with options if applicable]
My suggestion: [Your recommended direction/answer if you have one]"
Phase 2: Section-by-Section Design Presentation
Once you have sufficient understanding:
- Present Design in Sections: Present your design specification in sections of 200-300 words each
- Seek Confirmation: After each section, ask the user if it looks correct before proceeding
- Iterative Refinement: If the user indicates a section needs changes, revise it based on their feedback before moving to the next section
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 · 64 lines · 14 tokens per session scan A 3238c549bd99
dev-product-brainstorm is a command published in the GitHub repository AlteredCraft/claude-code-plugins (13 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 715 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.