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/softspark/ai-toolkit/brainstormnpx skills add softspark/ai-toolkit --skill brainstormgit clone --depth 1 https://github.com/softspark/ai-toolkitWhat 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 | $0.00048 | $0.01890 |
| Opus 5 | $0.00024 | $0.00945 |
| Sonnet 5 | $0.00010 | $0.00378 |
| Haiku 4.5 | $0.00005 | $0.00189 |
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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm
$ARGUMENTS
The conversation that happens before an artifact exists. Every other planning skill here produces something — a PRD, a plan, issues, a design. This one is allowed to produce nothing, and that is its point.
The zero option is a real candidate
Price "build nothing" against the proposal properly. Not as a strawman, not as a sentence acknowledged and moved past — as a genuine option with its own costs:
- what breaks or stays broken if nobody does this
- who currently absorbs that, and how much it costs them
- how long the problem has existed without being fixed, and what that says about it
- what the codebase carries forever once this exists: another surface, another migration path, another thing that has to keep working
If the zero option wins, say so and stop. Do not invent a deliverable to justify the conversation. A brainstorm that ends in "this is not worth building, and here is what it would have cost" has done its job.
Steps
Step 1: Understand before proposing
Explore the actual codebase before shaping anything. Read what exists, grep for prior attempts, check whether the problem is already solved somewhere.
Ask what the user is trying to achieve, not what they want built. The stated request is a proposed solution; the problem behind it is what matters. Keep asking until you can state the problem without naming the solution.
Step 2: Shape the options
Produce at least three genuinely different approaches, one of which is always "do nothing / do it manually / wait". Different means different in kind, not three variants of the same shape.
For each: what it costs, what it forecloses, what has to stay true for it to keep working.
Step 3: Resolve the unknowns
List what nobody in the conversation actually knows. For each, decide whether it can be resolved now (read the code, check the data, run something) or whether it stays open and becomes a risk the next stage inherits.
Resolve what is cheap to resolve. An unknown carried into a PRD becomes an Open Question; an unknown carried past a PRD becomes a bug.
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.
- 2d ago First seen · 175 lines · 48 tokens per session scan A bd5b52fbc9df
brainstorm is a skill published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,890 once invoked, about $0.0002 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
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
opencode-bedrock-doc-blocks
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.