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/juan294/cc-rpi/brainstormgit clone --depth 1 https://github.com/juan294/cc-rpiWrote 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/juan294/cc-rpi/brainstorm)<a href="https://agentmods.dev/commands/juan294/cc-rpi/brainstorm"><img src="https://agentmods.dev/badge/commands/juan294/cc-rpi/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 | $0.00000 | $0.00709 |
| Opus 5 | $0.00000 | $0.00354 |
| Sonnet 5 | $0.00000 | $0.00142 |
| Haiku 4.5 | $0.00000 | $0.00071 |
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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine a raw idea into a validated design brief: $ARGUMENTS
Model tier: opus — Opus session. Conversational reasoning, no subagents by default.
The front end of RPI for greenfield or vague work. /research documents an
existing codebase; /brainstorm interrogates an idea that does not exist yet and
produces a design brief that /plan can consume. Use it when the request is a
goal, not a spec — when you could not yet write success criteria.
When to use
- Greenfield feature or project with no clear spec.
- A vague request ("we should make X better") where scope is undefined.
- Skip it when the task is well-specified, mechanical, or already researched.
Go straight to
/plan(existing code) or/research(understand first).
Process
- Restate the idea in one sentence and name the core uncertainty. If the
one-liner is obvious and unambiguous, say so and recommend skipping to
/plan— do not manufacture questions. - Ask ONE focused question at a time. Wait for the answer before the next. Never batch a wall of questions. Socratic, not a survey.
- Cover the dimensions that change the design, in roughly this order:
- Problem: who has it, what do they do today, why now.
- Scope: what is explicitly IN and OUT of this effort.
- Constraints: stack, deadlines, existing systems, non-negotiables.
- Success: how we will know it worked — concrete, observable.
- Risks: what could make this the wrong thing to build.
- Present design options as they emerge — at least two, with honest trade-offs. Recommend one. Do not hide the alternatives.
- Reflect understanding back in digestible chunks. Confirm each chunk before moving on. Surface disagreements early, not at the end.
- When the uncertainty is resolved, write the design brief.
Output
Save to docs/research/YYYY-MM-DD-[description]-brief.md (same directory /plan
reads from). Structure:
# Design Brief: [name]
> Brainstormed on [date]
## Problem
[Who, what they do today, why now]
## Goal
[One sentence]
## Scope
**In:** [...]
**Out:** [...]
## Constraints
[Stack, deadlines, existing systems, non-negotiables]
## Chosen Approach
[The recommended option and WHY, with the rejected alternatives and why not]
## Success Criteria
[Concrete, observable — these become the plan's success criteria]
## Open Risks
[What could still make this wrong]
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.
- 4d ago First seen · 78 lines · 0 tokens per session scan A f7d7b475160c
brainstorm is a command published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 709 tokens. 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 2026-08-31.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
test
Generate comprehensive tests.
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.