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 agentmods add skills/bigmacfive/appbun/appbun-web-desktopnpx skills add bigmacfive/appbun --skill appbun-web-desktopgit clone --depth 1 https://github.com/bigmacfive/appbunWrote 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/bigmacfive/appbun/appbun-web-desktop)<a href="https://agentmods.dev/skills/bigmacfive/appbun/appbun-web-desktop"><img src="https://agentmods.dev/badge/skills/bigmacfive/appbun/appbun-web-desktop.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01124 |
| Opus 5 | $0.00032 | $0.00562 |
| Sonnet 5 | $0.00013 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
appbun-web-desktop 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
appbun Web Desktop
Use appbun when the user wants a fast URL -> desktop app workflow that still leaves an editable Electrobun project.
Default Workflow
- Identify the target URL or local dev server.
- If the user is inside a web app repo and a dev server may already be running, try
appbun dev --name "<App Name>" --out-dir ../appbun-output/<app-slug> --yes. - Existing web app repo: prefer the running local URL, often
http://localhost:3000. - Public website: use the canonical HTTPS URL.
- Known app idea: check recipes with
appbun recipesorappbun discover <concept>.
- If the user is inside a web app repo and a dev server may already be running, try
- Choose a scoped output directory.
- Existing repo: default to a dedicated sibling or workspace directory such as
../appbun-output/<app-slug>. - Only write inside the source repo after the source app is committed or backed up.
- Standalone wrapper: default to
./<app-slug>.
- Existing repo: default to a dedicated sibling or workspace directory such as
- Generate the wrapper.
- Existing local app, auto-detect common dev ports:
npx -y appbun@latest dev --name "<App Name>" --out-dir ../appbun-output/<app-slug> --yes - Existing app repo:
npx -y appbun@latest <url> --name "<App Name>" --out-dir ../appbun-output/<app-slug> --yes - Known recipe:
npx -y appbun@latest chatgpt --out-dir ./desktop/chatgpt --yes
- Existing local app, auto-detect common dev ports:
- Install and verify inside the generated wrapper.
cd ../appbun-output/<app-slug> appbun doctor --project appbun package --install - Run diagnostics when builds fail or before release.
npx -y appbun@latest doctor npx -y appbun@latest doctor --target macos npx -y appbun@latest doctor --project ../appbun-output/<app-slug> npx -y appbun@latest doctor --target linux
Agent Prompt Mode
When the user wants a prompt for another coding agent instead of direct scaffolding, generate one:
npx -y appbun@latest prompt http://localhost:3000 --name "<App Name>"
Use --copy only when clipboard access is acceptable.
What ships with it
2 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.
- 4d ago First seen · 97 lines · 64 tokens per session scan A 8dbd4e2e8b65
appbun-web-desktop is a skill published in the GitHub repository bigmacfive/appbun (97 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,124 once invoked, about $0.0003 per session on Opus 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
compose:subagent
Use when executing implementation plans with independent tasks in the current session.
compose:plan
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-creator
Use when creating, updating, packaging, or validating an Lfcode skill. Covers normal user-managed skills stored under the Lfcode data directory skills/ / and built-in bundled skills shipped from packages/lfcode/src/skill/lfcode/.bundle/ /.
desktop-releases
Guide for building and releasing the Open Sunsama desktop app across all platforms.
versioning
Manage software versions across the Open Sunsama monorepo. Use when releasing new versions, updating version numbers, building apps for distribution, or when any version-related task is mentioned. Triggers on keywords like "version", "release", "v1.x.x", "bump", "publish", "deploy app".
playwright-browser
Use when controlling browser pages with Playwright MCP in Lfcode; guides navigation, screenshots, interaction, and reuse of hidden or collapsed embedded side browser targets instead of the Electron app shell.