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 awizemann/scarf --skill scarf-miniapp-authorgit clone --depth 1 https://github.com/awizemann/scarfWrote 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/awizemann/scarf/scarf-miniapp-author)<a href="https://agentmods.dev/skills/awizemann/scarf/scarf-miniapp-author"><img src="https://agentmods.dev/badge/skills/awizemann/scarf/scarf-miniapp-author/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/awizemann/scarf/scarf-miniapp-author"><img src="https://agentmods.dev/badge/skills/awizemann/scarf/scarf-miniapp-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 89 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00078 | $0.03132 |
| Opus 5.5 | $0.00031 | $0.01253 |
| Sonnet 5.5 | $0.00016 | $0.00626 |
| Haiku 4.5 | $0.00008 | $0.00313 |
Grade A, and why
scarf-miniapp-author 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 1mo 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scarf Mini-App Author
Build a mini-app: a small web surface (HTML/CSS/JS) that Scarf renders inside a project's cockpit (the "Mini-apps" panel) over a narrow, versioned JS bridge (window.scarf). A mini-app is a project facet — it lives in the project directory and is bound to the project (and, for scarf.prompt, a dedicated Hermes agent session). Because it's plain web + a tiny API, you can author one reliably with your file tools.
When to invoke this skill
- "Build me a mini-app that …" / "Add a little app to this project for …"
- "Make a panel that shows / lets me …" (a task list, an approval queue, a status board, a chart, a form).
- During a project upgrade (the
scarf-template-authorupgrade flow), to add a starter mini-app or two.
Do not invoke for: editing the project's dashboard.json (that's the Dashboard panel — use widgets), or pure reference questions (answer inline from below).
Where a mini-app lives
<project>/.scarf/miniapps/<id>/
├── miniapp.json # manifest (REQUIRED)
├── index.html # entry document (REQUIRED; default entry name)
└── … # any local CSS/JS/images, referenced by RELATIVE path
<id>is the directory name and is canonical — it must equalminiapp.json.id. Use a short kebab-case slug (e.g.task-board).- Scarf discovers the mini-app automatically once the dir +
miniapp.jsonexist; no registration step.
The manifest — miniapp.json
{
"id": "task-board",
"name": "Task Board",
"version": "1.0.0",
"entry": "index.html",
"minBridgeVersion": "1.0",
"permissions": ["query:kanban.tasks"],
"panelHint": { "preferredWidth": 480, "placement": "panel" },
"generated": true
}
- Only
id+nameare required;entrydefaults toindex.html,permissionsto[](default-deny),minBridgeVersionto"1.0",generatedtofalse. - Set
"generated": truefor anything you author — it labels the app as agent-written in the cockpit and on the permission sheet. It no longer buys or costs permissions (sensitive ones are off for everyone), so claiming otherwise gains nothing; be honest. permissionsmust list every bridge surface the app uses (default-deny — an undeclared call is refused).- Raise
minBridgeVersiononly for a surface you actually need —"1.1"forscarf.openURL. An older Scarf refuses the app outright rather than half-running it.
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.
- 1mo ago Changed · -1 lines b942e580a6eb
- 1mo ago Changed · +44 lines c18279ac8291
- 1mo ago First seen · 152 lines · 78 tokens per session scan A 068050e582f5
scarf-miniapp-author is a skill published in the GitHub repository awizemann/scarf (898 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 3,132 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 2026-08-30.
Other skills, from other repositories
awesome-swift-macos-apps-docs
Use when adding, updating, or validating app entries in the awesome-swift-macos-apps repository, especially when maintaining both README.md and README.zh.md with concise one-sentence descriptions, correct category placement, and consistent bilingual formatting.
peekaboo
Use Peekaboo for macOS screenshots, Accessibility inspection, and background app/window/UI automation, including fallback computer use when the primary tool cannot handle an authorized task.
homekit
Control HomeKit smart home accessories and view home events via homeclaw-cli. Use when the user asks to control lights, locks, thermostats, fans, blinds, scenes, check device/sensor status, or view recent home activity/events. Examples: "turn off the stairs lights", "lock the front door", "what's the temperature"…
homeclaw
Control HomeKit smart home accessories via HomeClaw MCP tools. Also includes reference data for accessory categories, characteristics, and value formats. This skill should be used when the user wants to: Turn lights on or off, set brightness, or change color temperature Lock or unlock doors Set thermostat temperature…
envlatch
Run local commands with API keys stored in EnvLatch instead of copying credentials between .env files or shell profiles. Use when an agent, CLI, script, SDK, test, or build needs a saved credential environment variable on macOS.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…