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 skills/cookys/autopilot/brainstormnpx skills add cookys/autopilot --skill brainstormgit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00166 | $0.00850 |
| Opus 5 | $0.00083 | $0.00425 |
| Sonnet 5 | $0.00033 | $0.00170 |
| Haiku 4.5 | $0.00017 | $0.00085 |
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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brainstorm — discover the design before any code exists
The discriminator vs neighbours: do the options exist yet?
- No options yet / fuzzy need →
brainstorm(this skill) — explore, then converge on a design. - Options on the table, need to decide →
think-tank(multi-perspective) /think-tank-dialectic. - Need to know what others do →
survey(external research). - Approach already chosen → author the plan (
references/plan-template.md) →dev-flow.
This is a gate: do NOT invoke any implementation skill or write code until the user approves a design.
Protocol
1. Explore the real need — Socratic, ONE question at a time
Don't propose solutions yet. Ask one focused question, wait for the answer, then ask the next. Surface the actual problem, the constraints, the success picture, the no-go zones. Stop asking once you can restate the need in one sentence the user confirms. (One-at-a-time matters: a wall of questions gets a thin answer; a single sharp question gets a real one.)
2. Surface 2–3 genuinely different approaches
Not strawmen. Each approach: a one-line essence, its honest tradeoffs, what it's best/worst at. They must differ in kind (different architecture / different mechanism), not just in parameter. If you can only find one real approach, say so — that's a finding, not a failure.
3. Converge to a design spec
Once the user leans toward an approach, write a short design spec: the chosen approach, why it beat the others (1 line each), the key decisions made, and the open questions that remain. Keep it tight — it's the thing the plan will be built from, not the plan itself.
4. The approval gate
Present the design spec and ask for explicit approval. Nothing downstream runs without it. On approval, hand off:
- to
references/plan-template.mdto author the plan (thendev-flowto execute), or - directly to
dev-flowif the work is small enough to skip a formal plan. On "not yet" → keep exploring (back to step 1/2) — do not force forward.
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.
- 3d ago First seen · 57 lines · 166 tokens per session scan A 8c0916fa250d
brainstorm is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 166 tokens to every session and 850 once invoked, about $0.0008 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…