performance-hints

performance-hints is a skill for Claude Code, Codex from areu01or00/perf-hints. It costs 89 tokens per session (703 once invoked), scanned A, original, MIT.

A collection of general engineering guidance based on practices from Google's Abseil library. It covers performance, memory use, testing, code review, and API design.

In plain words
What is it for?
Use it when estimating costs, measuring performance, reducing memory allocations, debugging slow code, reviewing code, writing tests, designing APIs, or planning for scale.
Why use it?
It gives developers practical reference material for diagnosing slow or wasteful code and reviewing changes consistently.

Skill for Claude CodeCodex

Part of the perf plugin — 1 skill, 1 command, 2 agents shipped together

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/areu01or00/perf-hints/performance-hints
Any agent
npx skills add areu01or00/perf-hints --skill performance-hints
Clone the repo
git clone --depth 1 https://github.com/areu01or00/perf-hints

Made for: Claude Code, Codex.

Or install perf, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents.

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-hints

README.md
[![agentmods](https://agentmods.dev/badge/skills/areu01or00/perf-hints/performance-hints.svg)](https://agentmods.dev/skills/areu01or00/perf-hints/performance-hints)
Your own site
<a href="https://agentmods.dev/skills/areu01or00/perf-hints/performance-hints"><img src="https://agentmods.dev/badge/skills/areu01or00/perf-hints/performance-hints.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 703 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 $0.00089 $0.00703
Opus 5 $0.00044 $0.00351
Sonnet 5 $0.00018 $0.00141
Haiku 4.5 $0.00009 $0.00070

Measured 3d ago against content hash 7dc7f60b81bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-hints 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 3d 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-hints/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perf-Hints

Language-agnostic engineering wisdom from Google's Abseil - performance optimization, code review, testing, and software engineering practices.

Philosophy

"In established engineering disciplines a 12% improvement, easily obtained, is never considered marginal." — Donald Knuth

Don't dismiss small improvements. Twenty 1% improvements compound significantly.

Why "Optimize Later" Fails

  1. Flat profile problem - Performance lost everywhere, no obvious hotspot
  2. Library users suffer - They can't easily fix your slow code
  3. Heavy use constrains changes - Harder to change systems in production
  4. Expensive workarounds - Teams overprovision instead of fixing

Reference Routing

Consult the appropriate reference file based on the task:

User asks about Reference file
Back-of-envelope, estimation, costs references/when-estimating.md
Profiling, benchmarking, measurement references/when-measuring-performance.md
Memory, allocations, cache, GC references/when-optimizing-memory.md
"Why is this slow?", debugging perf references/when-debugging-perf.md
Code review, PR review references/when-reviewing-code.md
Testing, unit tests, mocking references/when-writing-tests.md
API design, interfaces, libraries references/when-designing-apis.md
Scaling, migrations, deprecation references/when-scaling.md
Finding a specific article references/index.md

Quick Reference

Latency Numbers

L1 cache                    0.5 ns
Main memory                  50 ns
Datacenter round trip       50 μs
Read 1MB memory             64 μs
Read 1MB SSD                 1 ms
Disk seek                    5 ms

Common Bottlenecks

Issue Pattern Fix
Sequential I/O for + await Parallelize
Client per request async with Client() Share client
N+1 queries Loop of DB calls Batch query
Hot loop allocations Object in loop Pre-allocate

Read the full file on GitHub · 70 lines

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. 3d ago First seen · 70 lines · 89 tokens per session scan A 7dc7f60b81bc

Subscribe to this mod's changes

performance-hints is a skill published in the GitHub repository areu01or00/perf-hints (4 stars, last pushed 8mo ago), licensed MIT. It adds 89 tokens to every session and 703 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens