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 MadAppGang/magus --skill 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/skills/madappgang/magus/bun)<a href="https://agentmods.dev/skills/madappgang/magus/bun"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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/madappgang/magus/bun"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00047 | $0.01164 |
| Opus 5 | $0.00023 | $0.00582 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00116 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun skill index — bunjs v0.2.2
You are holding the index, not the content. Its whole job is to tell you which one or two files to open, so you pay for the guidance a task needs and nothing else.
Read only what the task calls for. Opening all eight is ~4,000 lines and defeats the point of an index. Two is normal. Five means the task should be split.
The eight
Each path is relative to the directory holding this file — the other skills are its
sibling directories, which is true both when this ships as a plugin
(plugins/bunjs/skills/<name>/) and when it is installed as a project skill
(.claude/skills/<name>/).
Relative paths in a SKILL.md are resolved against that file's own directory — MEASURED
in benches/skill-router/ (RTR-1, --repeat 8, Sonnet 5) over 74 skill-file reads, with
no counterexamples. There is no reader for whom "the plugin's own directory" is a location;
the only thing an agent knows is where the file it just read lives. So ../<name>/ is not
a preference here, it is the only spelling that lands. A path that misses sends the reader
into a dead end, and in that run the ones who did not recover were every Recall failure.
| Read this | When the task is about | Ships |
|---|---|---|
../project-setup/SKILL.md |
starting or restructuring a project, folder layout, strict tsconfig, typed env config, workspaces, linting | env parser + 24 tests |
../http-service/SKILL.md |
an HTTP server or JSON API — Bun.serve routes, middleware, request context, response shape, streaming |
middleware + 38 tests |
../errors/SKILL.md |
error handling, validation boundaries, retry, timeout, circuit breaker, "make it fail gracefully" | AppError + 53 tests |
../testing/SKILL.md |
writing or fixing tests, bun:test, doubles, coverage gating, flaky tests |
harness + 30 tests |
../security/SKILL.md |
auth, passwords, tokens, injection, rate limiting, CORS, headers, secrets, security review | guards + 51 tests |
../production/SKILL.md |
shipping — graceful shutdown, structured logging, health checks, Docker, signals, CI | logger + 29 tests |
../performance/SKILL.md |
something is slow, benchmarking, event-loop blocking, profiling | bench harness + 18 tests |
../tui/SKILL.md |
a terminal UI — OpenTUI, dashboards, full-screen CLI | theme + 119 tests |
What ships with it
1 file 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.
- 9d ago First seen · 80 lines · 47 tokens per session scan A 1eec049da7b6
bun is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,164 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 skills, from other repositories
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
league-akari-shard-development
Use when creating, extending, refactoring, splitting, or reviewing League Akari main or renderer shards, including shard file organization, controller/loader/executor/handler boundaries, naming conventions, renderer TSX usage, platform guards, and public contract compatibility.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.