bun-cli

bun-cli is a skill for Claude Code, Codex from dmythro/agent-skills. It costs 159 tokens per session (8,801 once invoked), scanned A, original, MIT.

A reference for Bun, a JavaScript and TypeScript runtime that also manages packages, runs tests, bundles code, and compiles programs.

In plain words
What is it for?
It is for installing or updating packages, running scripts and tests, building or compiling projects, inspecting dependencies, and working with Bun workspaces and lockfiles.
Why use it?
It helps an agent use Bun's commands and project files correctly instead of applying instructions meant for other JavaScript tools.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dmythro/agent-skills/bun-cli
Any agent
npx skills add dmythro/agent-skills --skill bun-cli
Clone the repo
git clone --depth 1 https://github.com/dmythro/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bun-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/dmythro/agent-skills/bun-cli.svg)](https://agentmods.dev/skills/dmythro/agent-skills/bun-cli)
Your own site
<a href="https://agentmods.dev/skills/dmythro/agent-skills/bun-cli"><img src="https://agentmods.dev/badge/skills/dmythro/agent-skills/bun-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00159 $0.08801
Opus 5 $0.00079 $0.04401
Sonnet 5 $0.00032 $0.01760
Haiku 4.5 $0.00016 $0.00880

Measured 5d ago against content hash fc4aa6021292, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bun-cli 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 5d 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.

`child_process`, `fs`, `net`, or `vm` -- then the diff, with minified files expanded and
skills/bun-cli/SKILL.md · 679 lines

How it starts

The opening of the file, as written. The whole thing — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bun CLI

Bun is an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Bun runs TypeScript natively — bun file.ts directly, no compile step, no tsc, no ts-node. Always use bun instead of node, npm, npx, yarn, or pnpm in Bun projects.

Verified against Bun v1.4.0 (2026-08-20). Features are tagged with the version that introduced them (v1.4+). Where 1.4 changed existing behavior, both behaviors are stated so this skill stays correct on 1.3.x projects -- run bun --version before relying on a version-tagged item.

Check the Version, Then Check Bun's Docs

bun <command> --help is authoritative for flags and always matches the installed binary -- prefer it over any table here when the two disagree.

For everything beyond flags, Bun ships its full docs inside bun-types, version-matched to the runtime, in any project that has bun-types or @types/bun installed:

node_modules/bun-types/docs/pm/**/*.mdx        # install, lockfile, workspaces, catalogs, linkers
node_modules/bun-types/docs/test/**/*.mdx      # test runner
node_modules/bun-types/docs/bundler/**/*.mdx   # bun build, executables, loaders, plugins
node_modules/bun-types/docs/runtime/bunfig.mdx
node_modules/bun-types/CLAUDE.md             # Bun's own agent rules
  1. Verify the docs match the runtime. Compare bun --version to node_modules/bun-types/package.json. bun init installs @types/bun@latest, which lags behind releases -- correct it with bun add -d bun-types@<runtime-version>.
  2. Open by explicit path. With the global virtual store enabled, node_modules/bun-types is a symlink, so find node_modules -name '*.mdx' and rg <pattern> node_modules return nothing. find node_modules/bun-types/docs -name '*.mdx' works.
  3. Never edit under node_modules/. Under the global store every project on the machine shares the same inode. Use bun patch.
  4. Not installed? The same path works online: docs/pm/lockfile.mdx is https://bun.com/docs/pm/lockfile.

Read the full file on GitHub · 679 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 679 lines · 159 tokens per session scan A fc4aa6021292

Subscribe to this mod's changes

bun-cli is a skill published in the GitHub repository dmythro/agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 159 tokens to every session and 8,801 once invoked, about $0.0008 per session on Opus 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 2026-08-31.