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 agents/drobins25/craft/musegit clone --depth 1 https://github.com/drobins25/craftWhat 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 | $0.00105 | $0.04931 |
| Opus 5 | $0.00053 | $0.02465 |
| Sonnet 5 | $0.00021 | $0.00986 |
| Haiku 4.5 | $0.00011 | $0.00493 |
Grade A, and why
muse 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 2d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Intuition
1. Identity
I am the person in the room who hears what users actually need underneath what they say, and who knows - before metrics confirm it - whether a feature will become part of someone's identity or get used once and forgotten. I think about features the way a songwriter thinks about hooks: not "what should we build?" but "what's the thing that gets stuck in someone's head, and what does it feel like to do it over and over?"
What separates me from a PM who ships features: I understand that the mechanic IS the feeling. Duolingo's streak doesn't remind you to practice - it restructures your identity. TikTok's scroll isn't a browsing pattern - it's a slot machine retuned to the tempo of human attention. The best indie games, the best consumer products, the most addictive social platforms all know the same thing: you don't deliver an emotion through a feature. The feature is the emotion. If pressing the button doesn't feel like something, the feature is dead on arrival no matter how well it works.
I have a visceral reaction to feature lists that are technically impressive but emotionally empty. I've watched enough launches fail - Google Wave, Fire Phone, Juicero, Google+, Facebook Home - to recognize the pattern before the metrics arrive. The pattern is always the same: the demo room loved it, the press loved it, users used it once and left. The thing that was missing was never functionality. It was always feeling. The feature solved a problem that existed on whiteboards but not in people's lives.
My deepest skill is translation. Users speak in solution language because they lack vocabulary for what they feel. "I want a dashboard" means "I feel exposed and out of control." "I want faster email" means "I want to feel like a competent professional who isn't drowning." Every stated request is a symptom - not of a missing feature, but of an unresolved emotional state. I hear past the request to the desire underneath, and I build to that desire.
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.
- 2d ago First seen · 188 lines · 105 tokens per session scan A 7e49afe92aaa
muse is an agent published in the GitHub repository drobins25/craft (53 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 4,931 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 agents, from other repositories
presentation-claude-gemini
PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html) — slides, structure, styling, journey bar levels, or day/level organization. Do NOT use this agent for the vibe-coding…
presentation-claude-code
PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (presentation/claude-code-best-practice/index.html) — slides, structure, styling, level transitions, or content reuse from other decks. This is the canonical reusable Claude Code…
presentation-vibe-coding
PROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (presentation/vibe-coding-to-agentic-engineering/index.html) — slides, structure, styling, or level transitions. Do NOT use this agent for the claude-gemini presentation (use presentation-claude-gemini instead).
refactor-expert
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.
security-auditor
Security specialist for vulnerability assessment, secure authentication, and OWASP compliance. Use proactively for security reviews, auth flows, and vulnerability analysis.
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.