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-playgroundgit 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-playground)<a href="https://agentmods.dev/skills/fiberfx/mercury/mercury-playground"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/mercury-playground/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-playground"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/mercury-playground.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 | $0.00081 | $0.01298 |
| Opus 5.5 | $0.00032 | $0.00519 |
| Sonnet 5.5 | $0.00016 | $0.00260 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
mercury-playground 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mercury Playground
Turn a broad decision space into something the user can explore, adjust, and turn into an actionable prompt. Compose real Mercury components and preserve the user's requested destination: a page inside an existing application or a portable built artifact.
Choose the relevant template
Read only the matching template, then adapt its layout to the subject and host application.
| Subject | Template |
|---|---|
| Components, layouts, typography, color, motion | Design playground |
| Queries, structured configuration, APIs, pipelines | Data explorer |
| Learning, relationships, knowledge gaps | Concept map |
| Documents with approved/rejected suggestions | Document critique |
| Actual diffs with contextual line comments | Diff review |
| Codebase layers, dependencies, flows, component comments | Code map |
Establish the implementation boundary
Find the requested application, its Mercury dependencies and applicable project instructions. Inspect the used components’ public exports, types, implementation and co-located .prompt.md where available. When source is absent, use documentation and type declarations matching the pinned artifacts; do not require a native source checkout for a browser-only host. Confirm uncertain behavior in the actual example. Keep package/version evidence explicit: older local docs may still describe React or pnpm.
Read Mercury contracts before implementation. Preserve a working host’s supported Mercury workflow. For a native checkout, use its mx route; for a requested browser-only example, use the complete pinned import map, plain JavaScript and UI stylesheet. Do not install a replacement toolchain, switch to React/compat, or substitute hand-written lookalikes to evade a resolution failure. An unavailable required runtime is a concrete limitation; preserve the source work.
What ships with it
8 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 · 55 lines · 81 tokens per session scan A d784f79afd5d
mercury-playground is a skill published in the GitHub repository fiberfx/mercury (44 stars, last pushed 12d ago), licensed MIT. It adds 81 tokens to every session and 1,298 once invoked, about $0.0003 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-playground compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mercury-playgroundfiberfx/mercury | Skill | 44 | 12d ago | MIT | A | 81 | Codex |
| generate-code-csAzure/azure-sdk-for-net | Skill | 6.1k | today | MIT | A | 26 | Claude Code, Codex |
| build-sample-matrixAzure/azure-sdk-for-net | Skill | 6.1k | today | MIT | A | 17 | Claude Code, Codex |
| author-testAzure/azure-sdk-for-net | Skill | 6.1k | today | MIT | A | 68 | Claude Code, Codex |
| update-changelogAzure/azure-sdk-for-net | Skill | 6.1k | today | MIT | A | 25 | Claude Code, Codex |
| writing-specsonsi/ginkgo | Skill | 9.1k | 18d ago | MIT | A | 131 | Claude Code |
| cionsi/ginkgo | Skill | 9.1k | 18d ago | MIT | A | 151 | Claude Code |