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.
git clone --depth 1 https://github.com/MadAppGang/magusWrote 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/plugins/madappgang/magus/bunjs)<a href="https://agentmods.dev/plugins/madappgang/magus/bunjs"><img src="https://agentmods.dev/badge/plugins/madappgang/magus/bunjs/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/plugins/madappgang/magus/bunjs"><img src="https://agentmods.dev/badge/plugins/madappgang/magus/bunjs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bunjs 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 20d 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.
What it actually says
{
"name": "bunjs",
"version": "0.5.0",
"description": "Bun and TypeScript toolkit. A `/bunjs:bun` index routes any task to the right one of eight task-shaped skills — setup, HTTP, errors, testing, security, production, performance, TUI — each shipping copyable code verified against Bun. Only Bun is tested.",
"author": {
"name": "Jack Rudenko",
"email": "[email protected]",
"company": "MadAppGang"
},
"license": "MIT",
"homepage": "https://github.com/MadAppGang/magus",
"category": "development",
"keywords": [
"bun",
"bunjs",
"typescript",
"http",
"api",
"error-handling",
"resilience",
"testing",
"security",
"production",
"docker",
"performance",
"benchmarking",
"project-structure",
"tui",
"opentui",
"terminal-ui",
"node-best-practices",
"router",
"skill-index"
],
"skills": [
"./skills/bun",
"./skills/project-setup",
"./skills/http-service",
"./skills/errors",
"./skills/testing",
"./skills/security",
"./skills/production",
"./skills/performance",
"./skills/tui"
],
"compatibility": {
"claudeCode": ">=0.1.0"
}
}
What it installs
The manifest is a name and a version. 9 skills, 9 commands travel with it, and installing the plugin installs all of them — 660 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill tui A 52 tokens
- Skill errors A 39 tokens
- Skill http-service A 45 tokens
- Skill production A 48 tokens
- Skill project-setup A 50 tokens
- Skill security A 49 tokens
- Skill testing A 46 tokens
- Skill performance A 41 tokens
- Skill bun A 47 tokens
- Command bun A 32 tokens
- Command errors A 30 tokens
- Command http-service A 27 tokens
- Command performance A 25 tokens
- Command production A 22 tokens
- Command project-setup A 29 tokens
- Command security A 27 tokens
- Command testing A 23 tokens
- Command tui A 28 tokens
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.
- 20d ago Changed 9ed2b1e2bcbb
- 22d ago Changed cacd4a779c52
- 1mo ago Changed dc9e1bb2bff2
- 1mo ago First seen · 50 lines scan A 3c42a30a4bbd
bunjs is a plugin published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
vovk
Claude Code plugin for Vovk.ts — topic-based skills covering segments, procedures, validation, SSR, and project setup.
kamae-ts
Kamae (構え) — an extensible harness of skill plugins for designing and implementing robust server-side TypeScript applications.
nestjs-best-practices
NestJS 11+ best practices for enterprise Node.js applications with TypeScript.
coding
Programming skills: Python, TypeScript, FastAPI, Postgres, coding guidelines, and more.
oas
Adaptive API code generator that learns your project patterns and syncs with OpenAPI specs.
elysia-skill
Expert knowledge for building type-safe web applications with ElysiaJS, including validation, lifecycle hooks, Eden end-to-end type safety, and integrations.