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 bendrucker/claude --skill bungit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/bun)<a href="https://agentmods.dev/skills/bendrucker/claude/bun"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/bun/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/bendrucker/claude/bun"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/bun.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 | $0.00034 | $0.00461 |
| Opus 5.5 | $0.00014 | $0.00184 |
| Sonnet 5.5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
bun scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`Bun.spawn` spawns subprocesses with streaming I/O; `Bun.spawnSync` runs synchronously. Configure stdin/stdout/stderr, environment variables, and working directory. Check `exitCode` for errors. What it actually says
Bun
bunx
Put --bun before the executable name to force the Bun runtime over Node shebangs. Use -p/--package when the binary name differs from the package name (e.g., bunx -p @angular/cli ng).
Lockfile
bun.lock is a text-based lockfile. Resolve merge conflicts by regenerating it from origin/main with only the resolved manifests applied, never by hand.
Resolution
Runtime flags must precede the script path: bun --cwd ./packages/app run dev. Never use .js extensions in TypeScript imports — Bun resolves them natively.
Shell
Bun.$ is a tagged template for shell execution. Use response methods (.text(), .json(), .lines()) to extract output, .nothrow() to handle failures without exceptions, and pipe/redirect syntax to compose commands.
Subprocess
Bun.spawn spawns subprocesses with streaming I/O; Bun.spawnSync runs synchronously. Configure stdin/stdout/stderr, environment variables, and working directory. Check exitCode for errors.
File I/O
Bun.file() creates file handles with .text(), .json(), .arrayBuffer(), and .stream() methods. Bun.write() writes content to files or stdout/stderr. Both support streaming for large files.
Testing
Bun runs tests in a single process, not worker-per-file like Vitest or Jest. Set AGENT=1 to suppress passing test output.
What ships with it
7 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.
- 11d ago Changed 59fa081b3cbc
- 2mo ago First seen · 49 lines · 34 tokens per session scan A 79f6a8874bfb
bun is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 461 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
bun compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bunbendrucker/claude | Skill | 18 | today | MIT | A | 34 | Claude Code |
| typescript-rulesshinpr/claude-code-workflows | Skill | 713 | 4d ago | MIT | A | 39 | Claude Code |
| better-authsecondsky/claude-skills | Skill | 248 | 9d ago | MIT | A | 53 | Claude Code |
| bun-bundlersecondsky/claude-skills | Skill | 248 | 9d ago | MIT | A | 90 | Claude Code |
| bun-hot-reloadingsecondsky/claude-skills | Skill | 248 | 9d ago | MIT | A | 42 | Claude Code |
| knip-cleanupsuxrobGM/jobpilot | Skill | 111 | today | MIT | A | 79 | Claude Code |
| pulumi-best-practicespulumi/agent-skills | Skill | 79 | 7d ago | Apache-2.0 | A | 92 | Claude Code, Codex |