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/day1labs/openava/brainstormingnpx skills add Day1Labs/OpenAva --skill brainstorminggit clone --depth 1 https://github.com/Day1Labs/OpenAvaWrote 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/day1labs/openava/brainstorming)<a href="https://agentmods.dev/skills/day1labs/openava/brainstorming"><img src="https://agentmods.dev/badge/skills/day1labs/openava/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 | $0.00022 | $0.01321 |
| Opus 5 | $0.00011 | $0.00660 |
| Sonnet 5 | $0.00004 | $0.00264 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
brainstorming 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 4d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Ideas Into Designs
Use this skill to turn raw ideas into clear, approved plans before execution.
Hard Gate
Do NOT start execution actions until:
- A concrete recommendation or plan has been presented
- The user has approved next action
For very small, low-risk tasks, a concise recommendation is enough (full plan doc not required).
Why This Exists
"Simple" tasks still fail due to hidden assumptions. Good brainstorming reduces wrong turns by asking fewer, better questions.
Adaptive Depth Guidance
Adapt interaction depth by complexity and uncertainty:
- Low complexity: concise clarification, direct recommendation, one confirmation
- Medium complexity: brief alternatives and trade-offs
- High uncertainty: fuller plan details, written doc, and deeper self-review
Do not label modes explicitly with the user; adjust depth seamlessly.
Workflow Checklist (Complete In Order)
- Explore project context (relevant files, docs, recent changes)
- Ask only high-impact clarifying questions
- Generate options (count adapts to complexity) and rank by decision matrix
- Give one-line recommendation first, then brief rationale
- Confirm next action with the user
- If uncertainty/impact is high, write plan doc and run deeper self-review
- After approval, transition to execution
Process Rules
1) Explore Context First
- Inspect existing context and patterns before proposing changes
- Keep scope realistic
- If request is too large, split into sub-projects and plan only the first one now
2) Clarify With Key Questions Only
- Ask questions only when missing information would materially change the plan
- Keep a strict question budget: default 0-3 total questions for the planning phase
- Prioritize purpose, hard constraints, and success criteria
- Prefer multiple-choice and ask one question per turn when clarification is needed
- Skip questions when a reasonable assumption is low risk; state the assumption and continue
Stop Asking Condition
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.
- 4d ago First seen · 196 lines · 22 tokens per session scan A 5896edcaf903
brainstorming is a skill published in the GitHub repository Day1Labs/OpenAva (10 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,321 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
design
Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…
shortfilm-prompt
电影感 AI 视频提示词的 5 段式写法(Seedance / 小云雀 / Sora / 可灵 / 即梦通用),含 14 条翻车规避规则。挂给写视频提示词、分镜、短剧脚本的步骤。.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成(shogun-imagegenを使え)。.
Video Editor (FFmpeg)
AI-powered Video Editor with trimming, merging, effects, overlays, and export.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.
video-producer
视频制作全能工具,两种用法——(A) 端到端生产:从零做一支完整视频,出脚本、分镜、机位一致性、素材匹配、闸门、渲染、自检、交付;(B) 给定素材剪辑:已有几个片段要拼一下、给一个片段配音合成、剪辑烧字幕等,直接用 Stage 12 工具箱(assemble/clip-trim/audio-mix/timeline-compose/scene-compose/add-silent-audio/make-outro)。.