Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bigmacfive/appbunnpx agentmods add skills/bigmacfive/appbun/appbun-web-desktopWrote 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/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/bigmacfive/appbun/appbun-web-desktop"><img src="https://agentmods.dev/badge/skills/bigmacfive/appbun/appbun-web-desktop.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 | $0.00064 | $0.01124 |
| Opus 5.5 | $0.00026 | $0.00450 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo 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 (99 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,124 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
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.