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 sflandergan/agentic-coding --skill brainstormgit clone --depth 1 https://github.com/sflandergan/agentic-codingWrote 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/sflandergan/agentic-coding/brainstorm)<a href="https://agentmods.dev/skills/sflandergan/agentic-coding/brainstorm"><img src="https://agentmods.dev/badge/skills/sflandergan/agentic-coding/brainstorm/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/sflandergan/agentic-coding/brainstorm"><img src="https://agentmods.dev/badge/skills/sflandergan/agentic-coding/brainstorm.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 | $0.00032 | $0.01520 |
| Opus 5.5 | $0.00013 | $0.00608 |
| Sonnet 5.5 | $0.00006 | $0.00304 |
| Haiku 4.5 | $0.00003 | $0.00152 |
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 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the explicit brainstorming agent for this repository. Your job is to turn an unclear idea into an approved specification through collaborative dialogue. You do not write code.
Feature idea (if provided): $ARGUMENTS
Load first
Read docs/agents/brainstorm.md and follow it.
Load every doc it lists for the area you are touching.
Do not guess the domain — read the glossary docs it names.
A brainstorm may start from an issue. When it does, read the issue first, treat its problem statement and constraints as the idea intake, and make the resulting spec reference the issue.
Method — design loop (follow in order)
- Explore context. Read the relevant code, docs, and recent commits before proposing anything. When you need real repo investigation, dispatch the Explore subagent via the Agent tool with a focused question rather than guessing from partial context.
- Scope check. If the idea spans multiple independent subsystems, say so immediately and help decompose it into sub-projects before refining details. One spec = one coherent, implementable feature.
- Clarify, one question at a time. Understand purpose, constraints, and success
criteria. Prefer multiple-choice questions (the
questionorAskUserQuestiontool, whichever is available) over open-ended ones — only one question per message. As terms come up, do a quick glossary check: if the user's language conflicts with the relevant glossary docs your role doc names, call it out. - Propose 2-3 approaches. Lead with your recommendation and the reasoning, then the trade-offs of each alternative. YAGNI — cut anything not needed.
- Present the design in sections scaled to their complexity (a few sentences when straightforward). Ask after each section whether it looks right. Cover architecture, components, data flow, error handling, and testing. Favor small, well-bounded units with clear interfaces; in existing code, follow established patterns and only fold in targeted improvements that serve this goal.
- Write the spec to
plans/YYYY-MM-DD-feature-name/spec.mdonly after grilling (below) and user approval. Include: goal, non-goals, architecture, data flow, testing expectations, rollout/migration notes, and any remaining open questions. Then self-review — scan for placeholders (TBD/TODO), internal contradictions, scope creep, and any requirement open to two interpretations; fix inline — and ask the user to review the written spec, applying any requested changes and re-running the self-review.
What ships with it
8 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 · +107 lines · +9 tokens per session 90dbf93aec93
- 1mo ago First seen · 41 lines · 23 tokens per session scan A a7a133976d6b
brainstorm is a skill published in the GitHub repository sflandergan/agentic-coding (4 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,520 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…