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 skills/pleaseai/claude-code-plugins/use-bunnpx skills add pleaseai/claude-code-plugins --skill use-bungit clone --depth 1 https://github.com/pleaseai/claude-code-pluginsWhat 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 | $0.00241 | $0.02903 |
| Opus 5 | $0.00120 | $0.01452 |
| Sonnet 5 | $0.00048 | $0.00581 |
| Haiku 4.5 | $0.00024 | $0.00290 |
Grade C, and why
use-bun scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://bun.sh/install | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bun.sh/install | bash Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Spawning processes**: prefer `Bun.spawn()` / `Bun.$` over `node:child_process` — better defaults, streaming stdio, async iterators. How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
Verify the ask CLI is available (which ask). It is the primary tool for reading the exact Bun version installed in the project — it fetches the version-tagged source from GitHub once and caches it at ~/.ask/. If ask is not installed, fall back to the local bun binary's built-in help and the official docs at https://bun.com/docs (which always tracks the latest release).
Before writing Bun-specific code, detect the project's Bun version. The skill bundles a helper that resolves it in the correct priority order (.bun-version → package.json.packageManager → engines.bun → global bun):
# Resolve project pin; GitHub release tags use the `bun-vX.Y.Z` form
BUN_REF="bun-v$(${CLAUDE_SKILL_DIR}/scripts/resolve-bun-version.sh)" || exit 1
echo "$BUN_REF" # e.g. bun-v1.3.14
# Lockfile format — Bun migrated from binary bun.lockb to text bun.lock at 1.2.0
ls bun.lock bun.lockb 2>/dev/null
See references/versions.md for the resolution rules and the underlying script (scripts/resolve-bun-version.sh).
If Bun is not installed, install it once:
# Recommended — official installer
curl -fsSL https://bun.sh/install | bash
# Or via npm / brew / proto / asdf — see https://bun.com/docs/installation
Critical: Do Not Trust Internal Knowledge
Bun ships fast — APIs land, change shape, or move modules between minor releases. Common pitfalls from outdated training data:
Bun.serveroutes (routes: { "/users/:id": handler }) — requires Bun 1.2.3+. Before that you wrotefetch(req)with manual URL parsing. Do not suggestrouteson older versions.bun.lock(text JSONC) vsbun.lockb(binary) — Bun 1.2.0+ writesbun.lockby default (the text format was introduced as opt-in earlier and became the default at 1.2). Existingbun.lockbfiles migrate viabun install --save-text-lockfile --frozen-lockfile --lockfile-only. If you see both, the text one wins.- Catalogs (
catalog:/catalogs:inpackage.json/bunfig.toml) — added in Bun 1.2+. Not available earlier. - Isolated installs (
linker = "isolated") — added in Bun 1.2.x. Earlier versions only supporthoisted. bun:sql/Bun.SQL— Postgres client landed in Bun 1.2+; native MySQL/SQLite are different surfaces (bun:sqlitehas always existed).Bun.RedisClient/Bun.redis— Valkey/Redis client is recent (Bun 1.2.x). Older code uses third-party libs.bun build --compile— single-file executables stabilised in 1.1+; flags like--bytecode,--target=bun-linux-x64-baseline, and Windows cross-compile are newer.mock.module()— module mocking inbun:test. Stable across all current Bun releases; very old (early 1.0.x) versions only hadmock()for function-level mocks. If you need to support a specific pre-1.1 version, verify the API against that release's docs.Bun.$(shell) — promoted from experimental in Bun 1.0.24+. API stabilised since.trustedDependenciesinpackage.json— Bun does not run installed dependencies' lifecycle scripts by default for security; you must allowlist via this field. Different default than npm/yarn.
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.
- 2d ago First seen · 133 lines · 241 tokens per session scan C 622f4ad24e32
use-bun is a skill published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 241 tokens to every session and 2,903 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.