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 zpower426/datapowers --skill brainstorminggit clone --depth 1 https://github.com/zpower426/datapowersWrote 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/zpower426/datapowers/brainstorming)<a href="https://agentmods.dev/skills/zpower426/datapowers/brainstorming"><img src="https://agentmods.dev/badge/skills/zpower426/datapowers/brainstorming.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.02147 |
| Opus 5 | $0.00017 | $0.01073 |
| Sonnet 5 | $0.00007 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade B, and why
brainstorming scanned grade B with 1 finding 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 7d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Do NOT run any code, load any data, train any model, or begin any implementation until you have presented an analytical design and the user has approved it. This applies to every analysis regardless of perceived simplici How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Analysis Projects
Help turn analytical goals into fully formed designs and plans through structured collaborative dialogue.
Start by understanding the business context and data landscape, then ask questions one at a time to refine the approach. Once you understand the problem, present the analytical design and get user approval.
Anti-Pattern: "This Is Too Simple To Need A Design"
Every analysis goes through this process. A quick summary, a single model, a column exploration — all of them. "Simple" analyses are where unexamined assumptions create the most wasted work. The design can be short for truly simple tasks, but you MUST present it and get approval.
Checklist
You MUST create a task for each of these items and complete them in order:
- Understand business context — what decision does this analysis support? What's the success criteria?
- Explore data landscape — what data is available? What's the shape, source, time range?
- Ask clarifying questions — one at a time: target variable, known constraints, prior attempts, stakeholder requirements
- State 3+ business hypotheses — articulate specific, falsifiable hypotheses BEFORE any EDA (e.g., "we expect churn to correlate with payment failure rate")
- Baseline thinking first — ask "what would logistic regression achieve?" before proposing complex models
- Identify analytical risks — data quality concerns, potential leakage, class imbalance, temporal issues
- Propose 2-3 approaches — with trade-offs (complexity vs interpretability, speed vs accuracy)
- Define validation integrity — specify the exact train/val/test split strategy and the moment it must be applied (before any transformation)
- Present analytical design — in sections, get user approval after each section
- Write design doc — save to
docs/datapowers/specs/YYYY-MM-DD-<topic>-design.mdand commit - Self-review design — check for ambiguity, missing data requirements, undefined metrics
- User reviews written design — ask user to confirm the spec before proceeding
- Transition to planning — invoke
datapowers:writing-analysis-plansskill
What ships with it
2 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.
- 7d ago First seen · 235 lines · 35 tokens per session scan B abb5d97aedd4
brainstorming is a skill published in the GitHub repository zpower426/datapowers (1 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 2,147 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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-llm
A setup and control layer for running language models locally on a Mac with Apple silicon, so data can stay on the computer.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and…
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…