Borrowing it
Nothing to install: this file belongs to geleynse/gantry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geleynse/gantry/main/.claude/skills/frontend-dashboard/SKILL.mdgit clone --depth 1 https://github.com/geleynse/gantryWrote 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/geleynse/gantry/frontend-dashboard)<a href="https://agentmods.dev/skills/geleynse/gantry/frontend-dashboard"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/frontend-dashboard/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/geleynse/gantry/frontend-dashboard"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/frontend-dashboard.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 | $0.00054 | $0.02706 |
| Opus 5.5 | $0.00022 | $0.01082 |
| Sonnet 5.5 | $0.00011 | $0.00541 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
frontend-dashboard 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Dashboard — Gantry
The dashboard is a React 19 + Next.js 15 app, statically exported (output: 'export' in
server/next.config.ts) to server/dist/public/ and served as static files by the Express
server (src/app.ts). Confirm you're editing the right tree: src/app/ (routes),
src/components/ (shared UI), src/hooks/ (data/state), src/lib/ (utilities), src/shared/
(server↔frontend type contracts).
Architecture implications of static export
- No Next.js server at runtime. No SSR, no Route Handlers/API routes under
src/app/, no server actions, nocookies()/headers()server APIs. Every page is effectively a client bundle; nearly everypage.tsxstarts with"use client"and fetches data itself viafetch/hooks after mount (seesrc/app/facilities/page.tsxfor a representative example). - Dynamic routes need
generateStaticParams+dynamicParams = false. The only dynamic segment in the app issrc/app/agent/[name]/page.tsx. It hardcodes aSTATIC_AGENT_NAMESarray (comment: "Keep this in sync with fleet-config.json") and exportsgenerateStaticParams()returning that list plusexport const dynamicParams = false. Gotcha: if a fleet adds/removes an agent, that array must be updated and the client rebuilt, or the new agent's detail page 404s (static export can't dynamically match unlisted params). The actual page content lives inclient.tsx(AgentDetailClient) —page.tsxis just the static-params wrapper. - Two tsconfigs split the tree:
tsconfig.next.jsoncoverssrc/app/,src/components/,src/hooks/,src/lib/only (excludessrc/proxy/,src/web/,src/shared/). Don't import server-only modules (DB,src/proxy/*) into anything under those four dirs — it won't type-check and won't bundle innext build.
Dev loop — see the build-and-dev skill for full detail
One fact worth repeating because it burns people every time: bun run dev only watches the
server bundle and never rebuilds the dashboard. If you edit a .tsx under src/app/ or
src/components/ and the browser still shows old behavior, you didn't rebuild the client:
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.
- 2mo ago First seen · 172 lines · 54 tokens per session scan A 2c1f9fdc6514
frontend-dashboard is a skill published in the GitHub repository geleynse/gantry (4 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 2,706 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 2026-08-31.
frontend-dashboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontend-dashboardgeleynse/gantry | Skill | 4 | 2mo ago | MIT | A | 54 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |