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 mhylle/claude-skills-collection --skill deep-brainstormgit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/deep-brainstorm)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/deep-brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/deep-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/mhylle/claude-skills-collection/deep-brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/deep-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 170 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00105 | $0.06399 |
| Opus 5 | $0.00053 | $0.03200 |
| Sonnet 5 | $0.00021 | $0.01280 |
| Haiku 4.5 | $0.00011 | $0.00640 |
Grade A, and why
deep-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 11d 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 — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Brainstorm
Overview
This skill provides multi-session, resumable deep brainstorming that persists state to a mindmap-like directory structure on disk. Unlike brainstorm (single session, one output file) or team-brainstorm (single session, agent teams, one output file), deep-brainstorm spreads exploration across multiple sessions, building a rich interconnected knowledge structure over time.
Comparison:
| Aspect | brainstorm |
team-brainstorm |
deep-brainstorm |
|---|---|---|---|
| Sessions | 1 | 1 | Multiple (resumable) |
| Output | Single .md file |
Single .md file |
Directory tree |
| Methodologies | Socratic, Six Hats, SCAMPER, Premortem | Adversarial debate | All of the above + Morphological, TRIZ, Lateral Thinking, Lotus Blossom, Assumption Mapping, Reverse Brainstorming, HMW |
| Token cost | ~8-12K | ~25-40K | ~8-15K per session |
| Best for | Quick exploration | Critical decisions | Complex, multi-faceted topics |
| State | None | None | _mindmap.yaml on disk |
Critical Rules (READ FIRST)
These rules override any instinct to "be helpful by completing things quickly." This skill is intentionally slow and interactive.
Rule 1: NEVER Solve During SEED
The SEED phase maps the LANDSCAPE of areas to explore. It does NOT:
- Pick technologies or frameworks
- Recommend architectures
- Make decisions
- Produce any "answer" to the user's problem
SEED output is a set of QUESTIONS organized into areas, not answers.
Rule 2: NO Research During SEED
Do NOT spawn web-search-researcher or any research subagents during the SEED phase. Research happens in EXPLORE sessions, scoped to one area at a time. Researching everything up front kills the exploratory process by anchoring on early findings.
Rule 3: Minimum 3 Rounds of Socratic Questions
Before moving to area identification, you MUST complete at least 3 rounds of Socratic questioning with the user (2-4 questions per round). After each round, WAIT for the user to respond before asking more. Do NOT batch all questions into one message.
What ships with it
4 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.
- 11d ago First seen · 646 lines · 105 tokens per session scan A 462cefad8e42
deep-brainstorm is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It adds 105 tokens to every session and 6,399 once invoked, about $0.0005 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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.