performance-benchmarking

performance-benchmarking is a skill for Claude Code from the-open-agent/oss-skills. It costs 92 tokens per session (1,897 once invoked), scanned A, original, Apache-2.0.

A guide for measuring software speed and making performance claims that others can repeat and check.

In plain words
What is it for?
Use it to add benchmarks, compare projects, investigate slow code, or detect performance regressions in continuous integration.
Why use it?
It replaces guesses and vague claims with measurements, while helping find the code that actually takes the most time.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the oss-skills plugin — 18 skills shipped together

Good fit Use it to add benchmarks, compare projects, investigate slow code, or detect performance regressions in continuous integration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/the-open-agent/oss-skills/performance-benchmarking
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.

Any agent
npx skills add the-open-agent/oss-skills --skill performance-benchmarking
Clone the repo
git clone --depth 1 https://github.com/the-open-agent/oss-skills

Made for: Claude Code.

Or install oss-skills, the plugin that ships this one along with the rest of its 18 skills.

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-benchmarking

README.md
[![agentmods](https://agentmods.dev/badge/skills/the-open-agent/oss-skills/performance-benchmarking.svg)](https://agentmods.dev/skills/the-open-agent/oss-skills/performance-benchmarking)
Your own site
<a href="https://agentmods.dev/skills/the-open-agent/oss-skills/performance-benchmarking"><img src="https://agentmods.dev/badge/skills/the-open-agent/oss-skills/performance-benchmarking.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,897 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00092 $0.01897
Opus 5 $0.00046 $0.00949
Sonnet 5 $0.00018 $0.00379
Haiku 4.5 $0.00009 $0.00190

Measured 8d ago against content hash c7f999707960, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

performance-benchmarking 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 8d 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-benchmarking/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance and Benchmarking

"Blazing fast" in a README is worth nothing. A reproducible benchmark with a stated methodology is worth a great deal — and a benchmark that gets caught being unfair costs more than never publishing one.

Profile before you optimize

Non-negotiable order: measure → find the actual hot spot → change one thing → measure again. Programmer intuition about hot paths is wrong most of the time, and optimizing cold code adds complexity for zero benefit.

# Sampling profilers — start here
py-spy record -o profile.svg -- python app.py       # Python, no code changes
node --cpu-prof app.js                               # Node
cargo flamegraph --bench my_bench                    # Rust
go test -cpuprofile cpu.out -bench . && go tool pprof -http=: cpu.out
perf record -g ./binary && perf report               # anything on Linux

Read the flame graph for width, not height. Deep stacks are normal; wide frames are where time goes. And check allocation profiles too — in managed languages, GC pressure is frequently the real answer and never appears as an obvious hot function.

Benchmark methodology

A benchmark nobody can reproduce is marketing. Requirements:

  1. Warm up. JIT compilation, caches, connection pools. Discard the first N runs.
  2. Repeat and report distribution. Minimum, median, p95, p99 — and the shape. A single number hides bimodality, and the mean is the least useful statistic on a long-tailed distribution.
  3. Report variance. ±2% and ±40% are completely different claims.
  4. Control the environment. Pin CPU frequency where possible, disable turbo, close everything else, use a quiet machine. Never benchmark on a shared CI runner and present the numbers as authoritative.
  5. Publish the hardware and versions. CPU model, RAM, OS, kernel, runtime version, library versions, dataset. Without these the number is meaningless.
  6. Realistic workload. Benchmarking a parser on a 12-byte input measures function call overhead, not parsing.
  7. Verify correctness in the benchmark. A fast wrong answer is easy. Assert on the output — this also prevents dead-code elimination silently removing your workload.

Read the full file on GitHub · 164 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. 8d ago First seen · 164 lines · 92 tokens per session scan A c7f999707960

Subscribe to this mod's changes

performance-benchmarking is a skill published in the GitHub repository the-open-agent/oss-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,897 once invoked, about $0.0005 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

opentrons-dev-update

Guide users through setting up or updating a local development environment for the Opentrons opentrons/opentrons monorepo. Use this skill whenever a user mentions setting up or updating Opentrons development, cloning the Opentrons repo, installing or refreshing dev dependencies for Opentrons, getting started…

koji/opentrons-devenv-skill · 170 tokens

opentrons-dev-setup

Guide users through setting up a local development environment for the Opentrons opentrons/opentrons monorepo. Use this skill whenever a user mentions setting up Opentrons development, cloning the Opentrons repo, installing dev dependencies for Opentrons, getting started contributing to Opentrons, or hits errors…

koji/opentrons-devenv-skill · 164 tokens

cn-check

Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

continuedev/continue · 49 tokens

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Leonxlnx/taste-skill · 61 tokens

image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…

Leonxlnx/taste-skill · 116 tokens

brandkit

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…

Leonxlnx/taste-skill · 89 tokens