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 PaulRBerg/agent-skills --skill brainstormgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/brainstorm)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/brainstorm"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/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/paulrberg/agent-skills/brainstorm"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00708 |
| Opus 5 | $0.00024 | $0.00354 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
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 9d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Develop a non-obvious, useful concept through a focused creative interview, then return one substantial synthesis.
Workflow
- Extract the objective, audience, constraints, taste signals, and what feels stale about the obvious answers. Investigate facts available from the conversation, codebase, or supplied evidence instead of asking for them.
- Ask exactly one concrete question per turn. Format every question turn as
### 💡 Question <N> — <topic>, followed by**🧭 Context**, optional**🎯 Answer shape**, and**❓ Question**, with each label on its own line. Keep the context brief and put exactly one question in the final section. Use two to four concise examples or response anchors when they make an abstract choice easier to answer; do not turn them into an idea list. - Choose the question whose answer would most change the creative direction. Favor specific preferences, tensions, exclusions, emotional or practical effects, acceptable tradeoffs, and reactions to concrete contrasts. Avoid broad prompts that ask the user to do the ideation.
- Treat three to five questions as a soft target. Stop earlier when the prompt and answers already supply a strong
creative brief. Continue only while another answer could materially improve the final recommendation. Briefly
acknowledge an answer as
✅ Noted: <preference or implication>when useful; do not show progress recaps, candidate concepts, or interim synthesis. - Explore possibilities internally as the interview develops. Change lenses selectively through analogy, assumption reversal, an unrelated domain, another stakeholder, subtraction, combination, changed scale or time horizon, extreme constraints, or the useful fragment of a deliberately bad idea. Track promising fragments and rejected patterns, preserve genuinely distinct directions, and compare them against the user's evidence before converging.
- Once further questions would add little value, return the first full synthesis of the session. Make it materially
fuller than the question turns, concrete rather than exhaustive, and structured as:
### 🧭 Creative brief: objective, audience, constraints, and taste signals.### 💡 Recommended concept: the concept, how it works, and the experience it creates.### ✨ Why it could work: fit to the interview evidence and meaningful difference from obvious alternatives.- Optional
### 🔀 Strong alternatives: at most two genuinely different directions and their tradeoffs. - Optional
### ⚠️ Risks and open choices: only uncertainties that could change execution. ### 🧪 Smallest test: the minimal action and observable success signal.
- Do not end the completed brainstorm with another question. If the user explicitly asks to keep diverging or to stop the interview early, honor that request while preserving the same final-report shape when synthesis is requested.
What ships with it
1 file 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.
- 9d ago First seen · 47 lines · 48 tokens per session scan A 393e84a79d8e
brainstorm is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 708 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.