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 skills add the-open-agent/oss-skills --skill performance-benchmarkinggit clone --depth 1 https://github.com/the-open-agent/oss-skillsWrote 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/the-open-agent/oss-skills/performance-benchmarking)<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>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 5.1 | $0.00092 | $0.01897 |
| Opus 5 | $0.00046 | $0.00949 |
| Sonnet 5 | $0.00018 | $0.00379 |
| Haiku 4.5 | $0.00009 | $0.00190 |
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.
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:
- Warm up. JIT compilation, caches, connection pools. Discard the first N runs.
- 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.
- Report variance. ±2% and ±40% are completely different claims.
- 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.
- Publish the hardware and versions. CPU model, RAM, OS, kernel, runtime version, library versions, dataset. Without these the number is meaningless.
- Realistic workload. Benchmarking a parser on a 12-byte input measures function call overhead, not parsing.
- 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.
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.
- 8d ago First seen · 164 lines · 92 tokens per session scan A c7f999707960
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.
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…
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…
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.
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.
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…
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…