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 iurysza/android-use --skill brainstorminggit clone --depth 1 https://github.com/iurysza/android-useWrote 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/iurysza/android-use/brainstorming)<a href="https://agentmods.dev/skills/iurysza/android-use/brainstorming"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/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/iurysza/android-use/brainstorming"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/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 | $0.00036 | $0.00549 |
| Opus 5.5 | $0.00014 | $0.00220 |
| Sonnet 5.5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming
Use collaborative design before creative implementation. Understand the problem, expose meaningful choices, and agree on a direction before writing code.
Do not force this workflow onto trivial, mechanical, or already-specified work.
1. Understand the context
Inspect repository instructions, relevant files, existing patterns, prior decisions, and nearby behavior before proposing a design. Ask the user only for judgments the repository cannot answer.
Restate the intended outcome in a few sentences. Correct misunderstandings before exploring solutions.
2. Resolve discovery depth
Use the lightest available question tool for one quick decision. When the idea needs formal scope, several material decisions, testable facts, and an execution plan, hand it to the setup-goal skill rather than recreating that workflow here.
Brainstorming explores design direction. setup-goal turns an agreed direction into an implementation contract.
3. Explore approaches
Propose two or three meaningfully different approaches. For each, explain:
- the core idea;
- what it optimizes for;
- important trade-offs;
- fit with existing project conventions;
- what would make it the wrong choice.
Recommend one approach and explain why. Avoid fake alternatives that differ only cosmetically.
4. Present the design incrementally
Present the proposed design in small, coherent sections and ask whether each section is correct before continuing. Cover only what the work needs, such as:
- user or operator flow;
- components and responsibilities;
- data and state transitions;
- boundaries and integrations;
- failure behavior;
- testing and verification.
Return to unresolved sections when feedback changes an earlier assumption.
5. Capture the approved design
Write durable design Markdown under:
ai-artifacts/plans/YYYY-MM-DD-<topic>-design.md
Keep related sketches and diagrams embedded in that Markdown as ASCII or Mermaid. Do not create standalone diagram files unless the user explicitly requests another format.
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 First seen · 76 lines · 36 tokens per session scan A 68d9eccaf0a1
brainstorming is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 549 once invoked, about $0.0001 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 2026-09-15.
Other skills, from other repositories
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.