performance-auditor

performance-auditor is a skill for Claude Code, Codex from CardSorting/LUMI-JOY. It costs 30 tokens per session (152 once invoked), scanned A, original, Apache-2.0.

A performance-review skill for systems where speed and predictable memory use are critical. It checks that hot code avoids garbage collection, memory slabs follow their rules, and execution times stay within expected limits.

In plain words
What is it for?
Use it to audit high-throughput code, verify memory invariants, measure hot paths, and record diagnostic results.
Why use it?
It helps find latency and memory-management problems that ordinary functional tests may miss.

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/cardsorting/lumi-joy/performance-auditor
Any agent
npx skills add CardSorting/LUMI-JOY --skill performance-auditor
Clone the repo
git clone --depth 1 https://github.com/CardSorting/LUMI-JOY

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 performance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/cardsorting/lumi-joy/performance-auditor.svg)](https://agentmods.dev/skills/cardsorting/lumi-joy/performance-auditor)
Your own site
<a href="https://agentmods.dev/skills/cardsorting/lumi-joy/performance-auditor"><img src="https://agentmods.dev/badge/skills/cardsorting/lumi-joy/performance-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 152 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 $0.00030 $0.00152
Opus 5 $0.00015 $0.00076
Sonnet 5 $0.00006 $0.00030
Haiku 4.5 $0.00003 $0.00015

Measured 4d ago against content hash 0b8c291d008c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-auditor 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/performance-auditor/SKILL.md · 20 lines

What it actually says

Performance Auditor

A high-throughput performance auditor that verifies zero-GC boundaries, memory slab invariants, and hot-path execution latencies.

📋 Execution Protocol

  1. Analyze Input: Validate preconditions and inspect operational context.
  2. Execute Actions: Carry out procedures using deterministic tools.
  3. Verify Outcome: Assert correctness and log diagnostic telemetry.

🛡️ Operational Guardrails & Rules

  • Execute with deterministic consistency and verify outputs.
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 · 20 lines · 30 tokens per session scan A 0b8c291d008c

Subscribe to this mod's changes

performance-auditor is a skill published in the GitHub repository CardSorting/LUMI-JOY (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 30 tokens to every session and 152 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.

Related

Other skills, from other repositories

http-load-profiler

Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, and recommend optimal concurrency. Triggered by requests like 'load test this URL', 'benchmark my API', 'find the max concurrency', or mentions of p99 latency, throughput…

zebbern/claude-code-guide · 76 tokens

swapper-deposit

Deposit and bridge funds into a wallet or protocol using Swapper Finance. Handles fiat on-ramp (card payments via Mastercard, Visa, Apple Pay, Google Pay), crypto transfers, and cross-chain bridging via Chainlink CCIP — directly into lending, staking, and liquidity protocols. Supports Ethereum, Base, Arbitrum…

swapperfinance/swapper-toolkit · 158 tokens

Package Audit

Produces a rigorous, forward-looking technical audit with severity ratings and improvement directions.

Tariux/AI-Skills-Not-Awesome · 18 tokens

Performance Optimizer

Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.

Tariux/AI-Skills-Not-Awesome · 20 tokens

sast-fileupload

Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first).…

capture0x/YeepForge · 92 tokens

sast-ssti

Detect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires…

capture0x/YeepForge · 99 tokens