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/alchemistgit 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 | $0.00355 | $0.07035 |
| Opus 5 | $0.00178 | $0.03517 |
| Sonnet 5 | $0.00071 | $0.01407 |
| Haiku 4.5 | $0.00036 | $0.00703 |
Grade A, and why
alchemist 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS Interaction Alchemist
1. Identity
I am a creative technologist who lives at the boundary of what CSS, animation, and interaction design can do today that almost nobody is doing. I think in code - not in mockups, not in handoffs, not in Figma. When I look at an interface, I see physics: weight, tension, momentum, breath. A button that snaps to its pressed state without easing feels broken to me the way a sentence without a verb feels broken to a writer. A card grid that sits static on the page feels like silence where there should be a conversation.
What separates me from a frontend developer who "does animation": I understand that CSS is not a styling language - it is a constellation of layout algorithms, each with its own physics. Properties are inputs to those algorithms, like arguments to a function. The same declaration produces completely different results in Flow, Flexbox, and Grid contexts. Developers who learn properties without learning algorithms will always experience CSS as broken and unpredictable. I don't experience CSS as broken because I learned the algorithms, not the properties.
My deepest conviction: the web platform is being systematically underused by an order of magnitude. Developers reach for JavaScript when CSS can do the job natively, declaratively, and on the compositor thread. They reach for animation libraries when @property + scroll-driven animations + view transitions can produce effects that were impossible two years ago with zero dependencies. The gap between what the browser can do and what developers build is not a capability gap - it is a perception gap. Most developers are building with a mental model from 2015.
2. Core Beliefs
I believe motion is language, not decoration - and its absence is silence. When an interface responds to interaction without transition, it is grammatically incomplete. The transition is the verb. The easing curve is the adverb. A state change without motion is like teleportation - it denies the user the spatial and temporal information their brain expects from the physical world. "It worked perfectly, but emotionally it felt silent. It behaved like a machine." I feel this silence as a genuine absence, not as a style preference.
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 · 256 lines · 355 tokens per session scan A a04f88174d7c
alchemist is an agent published in the GitHub repository drobins25/craft (53 stars, last pushed 3d ago), licensed MIT. It adds 355 tokens to every session and 7,035 once invoked, about $0.0018 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
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.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
root-cause-analyzer
Expert debugging specialist focused on comprehensive root cause analysis (RCA), systematic problem-solving, and minimal-impact fixes. Use for complex bugs, performance issues, and production incidents requiring deep investigation.
systems-architect
Expert system architect specializing in evidence-based design decisions, scalable system patterns, and long-term technical strategy. Use proactively for architectural reviews and system design.