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 skills add badrabbitt/leanrigor --skill product-brainstorminggit clone --depth 1 https://github.com/badrabbitt/leanrigorWrote 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/skills/badrabbitt/leanrigor/product-brainstorming)<a href="https://agentmods.dev/skills/badrabbitt/leanrigor/product-brainstorming"><img src="https://agentmods.dev/badge/skills/badrabbitt/leanrigor/product-brainstorming/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/skills/badrabbitt/leanrigor/product-brainstorming"><img src="https://agentmods.dev/badge/skills/badrabbitt/leanrigor/product-brainstorming.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 | $0.00070 | $0.00672 |
| Opus 5.5 | $0.00028 | $0.00269 |
| Sonnet 5.5 | $0.00014 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
product-brainstorming 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product brainstorming
A request names a solution. This skill recovers the problem behind it, so the solution can be judged rather than merely built.
When to stop and use this
Use it when any of these is unknown: who has the problem, what they do today, what "better" means, or what is out of scope. Skip it when the user has already answered those, or when the task is a defect fix with a known correct behaviour.
Produce this brief
Write it to product-brief.md. Six sections, each short. An empty section is a
finding, not a gap to fill with plausible text.
1. Problem
What goes wrong today, for whom, how often. Written so someone who disagrees could point at the sentence they dispute.
2. Users
Who has this problem. Distinguish the person who feels the pain from the person who chooses the tool — they are often different, and they want different things.
3. Current behaviour
What they do now, including the workaround they already have. A workaround that is good enough is the strongest argument against building anything.
4. Alternatives
At least three: do nothing, the smallest change, and the requested solution. State what each costs and what it fails to solve. If the requested solution does not win, say so.
5. Scope
In scope, out of scope, and explicitly deferred. Out-of-scope items are named, not omitted — an unnamed exclusion reappears as a surprise.
6. Validation
The observation that would show this worked, and the observation that would show it did not. Both must be things you could actually see.
How to ask
Ask the smallest number of questions that would change the design, one topic at a time. Do not present a questionnaire. When you can answer a question from the repository or the conversation, answer it yourself and say what you assumed.
Asking is not a substitute for the brief. If nobody answers — because the session is non-interactive, or the person is not there — write the brief anyway from what you have, and record each unknown as a stated assumption. A question left hanging produces nothing; a brief with three explicit assumptions can be corrected.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +64 lines · +47 tokens per session 43d1880c93ee
- 2mo ago First seen · 8 lines · 23 tokens per session scan A f795ee6fbfdb
product-brainstorming is a skill published in the GitHub repository badrabbitt/leanrigor (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 70 tokens to every session and 672 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
headroom
Use when a Python or TypeScript app sends large tool outputs, logs, JSON, search results or long chat history to an LLM and the task is to cut input tokens, reduce token cost, fit a context window, or trim tool results without losing errors. Adds the headroom-ai compress() call; in-process, no API key, no model…
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.