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 fiberfx/mercury --skill mercury-design-buildergit clone --depth 1 https://github.com/fiberfx/mercuryWrote 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/fiberfx/mercury/mercury-design-builder)<a href="https://agentmods.dev/skills/fiberfx/mercury/mercury-design-builder"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/mercury-design-builder/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/fiberfx/mercury/mercury-design-builder"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/mercury-design-builder.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 | $0.00060 | $0.01334 |
| Opus 5.5 | $0.00024 | $0.00534 |
| Sonnet 5.5 | $0.00012 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
mercury-design-builder 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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mercury Design Builder
Make the requested interface useful, coherent, and demonstrably interactive. Compose genuine Mercury components; use application CSS for layout and supported tokens for styling. A polished screenshot, a successful build, and a working interaction establish different things.
For a new playground with live controls and a generated prompt, the available mercury-playground skill can supply that product workflow. Polishing an existing explorer remains in this skill: preserve its working exploration model and improve the requested surface.
Establish the boundary
Inspect the host route, entry point, styles, dependency manifests, and repository instructions before choosing an implementation. Keep an existing framework or build workflow unless migration is requested. A Mercury distribution bundle may contain documentation and a starter without the full module source tree.
Find the actual @fiberfx/ui and @fiberfx/hyperscript versions. For each component being changed, inspect its public exports, types, implementation, and co-located .prompt.md when available. Use the matching bundled documentation when source is absent. Resolve stale examples against those contracts; do not invent a prop, component, token, or package location. If prose and implementation disagree, record the version and discrepancy, inspect the affected behavior, and keep the explanation qualified until resolved. A successful import cannot resolve a behavioral disagreement.
Choose the smallest supported route:
| Available context | Route |
|---|---|
| Working application | Extend its conventions, pins, and existing tooling. |
Native Mercury starter and compatible mx |
Use its manifests and native development/build commands. |
| Simple standalone page with network access | Use the pinned browser example with import maps, plain JavaScript h/render, and the real UI stylesheet. Browsers do not parse TSX. |
| Portable offline artifact requested | Bundle real Mercury and account for all emitted assets; use the packaging guidance below. A CDN page does not satisfy this requirement. |
What ships with it
4 files 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.
- 5d ago First seen · 60 lines · 60 tokens per session scan A d849ec3e12a3
mercury-design-builder is a skill published in the GitHub repository fiberfx/mercury (44 stars, last pushed 12d ago), licensed MIT. It adds 60 tokens to every session and 1,334 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 2026-11-15.
mercury-design-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mercury-design-builderfiberfx/mercury | Skill | 44 | 12d ago | MIT | A | 60 | Codex |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.9k | today | MIT | A | 67 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 10.0k | 5d ago | Apache-2.0 | A | 24 | Claude Code, Codex |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 94 | Claude Code, Codex |