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 myths-labs/muse --skill brainstorminggit clone --depth 1 https://github.com/myths-labs/museWrote 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/myths-labs/muse/brainstorming)<a href="https://agentmods.dev/skills/myths-labs/muse/brainstorming"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/brainstorming/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/myths-labs/muse/brainstorming"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/brainstorming.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 | $0.00820 |
| Opus 5 | $0.00023 | $0.00410 |
| Sonnet 5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
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 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming — Reframe Before You Build
Inspired by gstack's /office-hours. Upgraded to output standardized design docs.
Overview
Don't just ask "what do you want to build?" Ask "what pain are you solving?"
This skill reframes the problem before a line of code is written, then outputs
a design doc that feeds into /sprint downstream skills.
The Process
Phase 1: Reframe the Problem
Before exploring solutions, challenge the framing:
- Listen for pain, not features. User says "add a dark mode toggle." Ask: "What's the actual problem? Is it eye strain? Brand consistency? User requests?"
- Push back on scope. User describes 10 features. Ask: "If you could only ship one this week, which one?"
- Challenge 3 premises. Identify the user's hidden assumptions and question them explicitly.
- "You're assuming users want X. What if they actually want Y?"
- "You're assuming this needs to be real-time. Does it?"
- "You're assuming mobile-first. What if desktop is the real use case?"
Rules:
- One question per message
- Multiple choice when possible
- Don't rush past reframing — this is the highest-leverage phase
Phase 2: Explore Approaches
Once the real problem is clear:
- Generate 3 approaches with different tradeoffs:
- Narrowest wedge — ship in hours, validate the thesis
- Balanced — ship in days, covers core use cases
- Full vision — ship in weeks, comprehensive solution
- Recommend one with clear reasoning
- Estimate effort for each (hours, not story points)
Lead with your recommendation. Explain why.
Phase 3: Present the Design
Once approach is chosen:
- Break into sections of 200-300 words
- After each section, ask: "Does this look right so far?"
- Cover: architecture, components, data flow, error handling, testing
- Apply ETHOS.md: Boil the Lake (do the complete thing), YAGNI (don't add what's not needed)
Phase 4: Output Design Doc
Write a standardized design doc to docs/plans/YYYY-MM-DD-<topic>-design.md:
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 · 102 lines · 45 tokens per session scan A 986538bfc7cb
brainstorming is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 820 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
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
evidence-attestation
Emit privacy-safe evidence attestations for agent actions, reviews, memory answers, handoffs, scores, approvals, and tool dispatches.
skill-policy-receipts
Use when a task must obey a hard project policy, such as "do not generate tests for internal services", "do not call production APIs", or "do not edit generated files". Emits a privacy-safe receipt before writes and after guard checks.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…