perf

perf is a skill for Claude Code, Codex from automagik-dev/genie. It costs 47 tokens per session (1,282 once invoked), scanned A, original, MIT.

A performance-review workflow for finding slow or resource-heavy parts of a codebase. It examines startup time, frequently run code, dependency size, and storage queries using measurements.

In plain words
What is it for?
Use it to assess performance and, when explicitly requested, make optimizations supported by before-and-after measurements.
Why use it?
It prevents developers from optimizing based on guesses and records the commands and results behind each performance claim.

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/automagik-dev/genie/perf
Any agent
npx skills add automagik-dev/genie --skill perf
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

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 perf

README.md
[![agentmods](https://agentmods.dev/badge/skills/automagik-dev/genie/perf.svg)](https://agentmods.dev/skills/automagik-dev/genie/perf)
Your own site
<a href="https://agentmods.dev/skills/automagik-dev/genie/perf"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/perf.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00047 $0.01282
Opus 5 $0.00023 $0.00641
Sonnet 5 $0.00009 $0.00256
Haiku 4.5 $0.00005 $0.00128

Measured 4d ago against content hash 93fecc839b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

perf 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 4d 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.

skills/perf/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Review

Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.

Lens

This lane begins performance work with measurement of the running system, never with intuition about the code. Every claim carries the command that produced it and the number it produced. The USE method frames each resource — utilization, saturation, errors. The most expensive performance bug is the one "fixed" without measuring before and after.

This lane's lens is inspired by the work of Brendan Gregg — author of Systems Performance, inventor of flame graphs and the USE method.

Mandate

Assess and report by default. Apply optimizations only when the invocation explicitly asks — and then only with a before/after measurement pair. Never report an estimate where a measurement is obtainable this session. Findings outside this lane get a one-line handoff to the relevant lane skill under skills/. When you have enough numbers to conclude, conclude.

Discover the Ground Truth First

Before measuring anything, establish what the product is and which latency its users actually feel: a CLI pays cold start per invocation (and per hook event, if it's invoked by hooks — the hook timeout is then the hard ceiling); a server pays per-request latency and saturation; a batch tool pays throughput. Read the entry points, the build config (bundling, minification, what's inlined), the manifest for dependency weight, and CLAUDE.md/AGENTS.md for stated performance constraints and deliberate tradeoffs (fork-per-event models, zero-daemon rules, chosen storage engines). Identify the shipped artifact users run — measure that, not the dev-mode path. Never carry numbers forward from documentation; a documented size or timing is a claim to re-measure.

Read the full file on GitHub · 52 lines

Files

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.

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. 4d ago First seen · 52 lines · 47 tokens per session scan A 93fecc839b65

Subscribe to this mod's changes

perf is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,282 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 2026-08-30.