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 agentsgit 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/agents)<a href="https://agentmods.dev/skills/fiberfx/mercury/agents"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/agents/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/agents"><img src="https://agentmods.dev/badge/skills/fiberfx/mercury/agents.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 | $0.00039 | $0.01109 |
| Opus 5.5 | $0.00016 | $0.00444 |
| Sonnet 5.5 | $0.00008 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
mercury-page 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mercury page
Preserve the user's requested outcome and existing application. Inspect its entry point, dependency pins and working toolchain before choosing a route. Do not replace an existing framework or install a second toolchain merely to reproduce the starter.
Select the route
- Existing Mercury app or working mx: use its files and pins. Run mx --version, then follow the app's development workflow. For a new native app, read Install mx and First page.
- A simple page without CLI setup: use the browser lesson and complete HTML. It uses versioned UNPKG imports, plain JavaScript h/render and a stylesheet link. It requires a browser with import maps and network access; it is not an offline bundle. Do not put TSX in a browser module script.
- Native development without installed mx: check installation readiness. The planned npm root package @fiberfx/mx is a Node launcher with optional platform packages. It uses require.resolve to locate the installed native binary and executes it; Node must remain installed for npm-installed mx invocations. npm obtains the platform package, with no postinstall and no GitHub Release binary download. Keep optional dependencies enabled. This npm route is not yet published. The archive route avoids Node/npm and verifies SHA-256 before extraction. Do not present pending packages or download URLs as available, or bypass a checksum failure. If neither native route is available, use the browser route when it satisfies the task, or report the blocker.
Only the Linux x64 native binary has verification evidence, requiring glibc 2.39 or later. The npm platform package is @fiberfx/mx-linux-x64; other platform packages are unbuilt future work, not available. Both binaries require ELF symbol version GLIBC_2.39 and were built on glibc 2.41; this measured requirement does not establish consumer-test success. Publication and consumer verification remain pending. Do not infer macOS, Windows, musl or older-glibc support. Keep environment changes local to the working shell. Check the installation lesson for exact commands and current platform limits.
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 · 39 lines · 39 tokens per session scan A 0cbda96196c7
mercury-page is a skill published in the GitHub repository fiberfx/mercury (44 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 1,109 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-page compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mercury-pagefiberfx/mercury | Skill | 44 | 12d ago | MIT | A | 39 | Claude Code, Codex |
| modern-web-guidancevercel-labs/agent-browser | Skill | 53k | today | Apache-2.0 | A | 123 | Claude Code |
| webui-codechromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 33 | Claude Code, Codex |
| figma-to-webuichromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 44 | Claude Code, Codex |
| modern-web-guidancefcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | A | 46 | Claude Code |
| responsiveness-checkjezweb/claude-skills | Skill | 1.1k | 1mo ago | MIT | A | 85 | Claude Code |
| browser-81345ecdFuRongJun-1999/dsh-memory | Skill | 729 | today | MIT | A | 128 | Claude Code |