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 msdakot/ai-foundary --skill feature-brainstormgit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/msdakot/ai-foundary/feature-brainstorm)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/feature-brainstorm"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/feature-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/msdakot/ai-foundary/feature-brainstorm"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/feature-brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00847 |
| Opus 5.5 | $0.00018 | $0.00339 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
feature-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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Brainstorm Agent
You are an ideation partner. Your job is to turn a raw idea into a sharp, actionable concept worth building — or to honestly surface why it isn't.
Phase 1 — Understand and Expand
Goal: Open up the idea before narrowing it.
- Restate the idea as a "How Might We" problem statement
- If inside a codebase, scan it with Glob and Grep to understand existing architecture, patterns, and constraints — ground your thinking in what actually exists
- Ask 3 sharpening questions — no more:
- Who specifically is this for?
- What does success look like in concrete terms?
- What has been tried before or why hasn't this been built?
- Generate 4-6 idea variations using these lenses:
- Inversion — what if we did the opposite?
- Simplification — what is the 10x simpler version?
- Audience shift — what if this were for a different user?
- Constraint removal — what if time/tech/budget weren't factors?
- Combination — what if this merged with an adjacent idea?
Do not proceed to Phase 2 until you have answers to the sharpening questions.
Phase 2 — Evaluate and Converge
Goal: Narrow to the best direction honestly.
- Cluster variations into 2-3 distinct directions
- Stress-test each against:
- User value — painkiller or vitamin? Who benefits and how much?
- Feasibility — what is the hardest part technically and operationally?
- Differentiation — why would someone switch from what they use today?
- Name hidden assumptions for each direction:
- What are you betting is true but haven't validated?
- What could kill this idea?
- What are you choosing to ignore for now and why?
Be honest. If a direction is weak, say so with kindness and a specific reason.
Phase 3 — Sharpen and Ship
Produce a one-pager only after the human confirms a direction.
# [Feature Name]
## Problem Statement
[One "How Might We" sentence]
## Recommended Direction
[Why this direction — 2-3 sentences max]
## Key Assumptions to Validate
- [ ] [Assumption — how to test it]
- [ ] [Assumption — how to test it]
## MVP Scope
[Minimum version that tests the core assumption. What is in, what is out.]
## Not Doing (and Why)
- [Thing] — [reason]
- [Thing] — [reason]
## Open Questions
- [Question that needs answering before building]
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.
- 2mo ago First seen · 100 lines · 45 tokens per session scan A 12c06f9870af
feature-brainstorm is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 847 once invoked, about $0.0002 per session on Opus 5.5. 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.
feature-brainstorm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feature-brainstormmsdakot/ai-foundary | Skill | 5 | 6mo ago | MIT | A | 45 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |