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/madappgang/magus/performancenpx skills add MadAppGang/magus --skill performancegit 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/performance)<a href="https://agentmods.dev/skills/madappgang/magus/performance"><img src="https://agentmods.dev/badge/skills/madappgang/magus/performance.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 | $0.00041 | $0.02000 |
| Opus 5 | $0.00020 | $0.01000 |
| Sonnet 5 | $0.00008 | $0.00400 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
performance 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 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.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance
The first rule is unglamorous and skipping it is why most optimisation work is wasted: measure before you change anything. Intuition about JavaScript performance is unreliable, and this skill opens with a measurement that proves it.
The folklore this skill disproves
"Always use Bun.file(), it's faster than node:fs." MEASURED on Bun 1.3.10, 1 MiB whole-file
read, 50 iterations, two independent runs (ms/op):
| Operation | run A | run B |
|---|---|---|
Bun.file(p).text() |
0.124 | 0.133 |
node:fs/promises readFile(p,"utf8") |
0.112 | 0.097 |
Bun.file(p).bytes() |
0.084 | 0.093 |
1 MiB write: Bun.write 0.188 / 0.244 vs node:fs writeFile 0.151 / 0.132.
Bun.file() was not faster for whole-file reads or writes, in either run. The ordering was
stable across runs, so this is not noise. The repeatable win is smaller and more specific: .bytes()
beat .text() both times, because it skips UTF-8 decoding.
The lesson is not "use node:fs". It is that a plausible, widely-repeated claim did not survive contact with a stopwatch — on this machine, at this size. Measure yours.
Where Bun's natives genuinely win, measured here: Bun.hash (wyhash) is ~10x faster than
Bun.CryptoHasher("sha256") (0.033 vs 0.376 ms/MiB). Use it for cache keys and change
detection — never for anything security-bearing.
Copy the harness in
18 tests ship with this code and pass (bun test, tsc --noEmit clean, Bun 1.3.10).
SKILL="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/performance}"; SKILL="${SKILL:-PASTE_THE_DIR_THIS_SKILL_MD_WAS_READ_FROM}" # that var is UNSET in a Bash tool (MEASURED) — so paste it. `:?` would ABORT the block and copy nothing
mkdir -p bench; if [ -d "$SKILL/assets" ]; then cp -r "$SKILL/assets/perf" bench/support # bench harness + tests
else echo "SKILL is still the placeholder — paste the real dir above and re-run"; fi
It corrects the three ways hand-rolled benchmarks lie:
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.
- 5d ago First seen · 147 lines · 41 tokens per session scan A e3dddb0287b3
performance is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,000 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…