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 commands/madappgang/magus/bungit 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/commands/madappgang/magus/bun)<a href="https://agentmods.dev/commands/madappgang/magus/bun"><img src="https://agentmods.dev/badge/commands/madappgang/magus/bun.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 5.1 | $0.00032 | $0.00389 |
| Opus 5 | $0.00016 | $0.00195 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
bun scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
<user_request>$ARGUMENTS</user_request>
-
Read
skills/bun/SKILL.md— resolved against this plugin's own directory (the tree this command was loaded from). It is the index: eight skills, what each is for, and the routing table for common tasks. -
Pick the one or two the request actually needs, and read only those. Match on what the task will make you write, not on the words used — "add login" is
security, "it's slow" isperformance. Chains stop where the task stops: a fresh app isproject-setup→http-service→errors;testingwaits until there is something to test,productionuntil it is being shipped. Reading all eight is ~4,000 lines and defeats the point of the index. -
Copy the shipped
assets/rather than retyping them. Six of the eight ship tested code and each names its exactcpline. Retyped versions silently lose the parts that matter — the enumeration-timing burn, full-jitter backoff, the cycle-safe cause walk. -
Before reporting done: satisfy the Acceptance section of every skill you read.
bun testandtsc --noEmitare the floor in all eight —bun runstrips types without checking them, so a type error never surfaces at runtime.
If the request is not Bun or TypeScript, say so and stop rather than guessing from these skills.
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.
- 6d ago First seen · 29 lines · 32 tokens per session scan A e4918fd438d4
bun is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 389 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.
setup-code-intelligence
Check code-intelligence prerequisites (ripgrep + a language server) and print install hints.
vite-react-setup
Setup project React SPA mới với Vite + TypeScript + Tailwind CSS v3 + Vitest. Dùng khi bắt đầu dự án frontend mới, cần scaffold đầy đủ config, brand KZTEK colors, và test setup sẵn sàng.
typescript
Apply TypeScript best practices and coding standards.
scaffold-react
Quickly scaffold a new React + TypeScript project with Claude Code configuration.
tsc
Use the TypeScript compiler to check for type errors in your codebase.