performance

A method for improving software speed by measuring current performance, locating the bottleneck, changing one thing, and measuring again.

In plain words
What is it for?
Use it to investigate slow code, latency, throughput, memory use, startup time, and performance regressions.
Why use it?
It prevents developers from optimizing based on guesses and makes the effect of each change visible.

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

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,214 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 $0.00050 $0.01214
Opus 5 $0.00025 $0.00607
Sonnet 5 $0.00010 $0.00243
Haiku 4.5 $0.00005 $0.00121

Measured 2d ago against content hash 0be2becab2c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance 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 2d 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/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance as Measurement

Overview

Optimize what you've measured, not what you suspect. Performance work without profiling is superstition. Measure first, hypothesize second, optimize third, measure again.

The Performance Loop

  1. Define the goal, What metric matters? Latency, throughput, memory, startup time?
  2. Measure the baseline, Quantify current performance with reproducible benchmarks
  3. Profile, Identify where time and resources actually go
  4. Hypothesize, What change would improve the bottleneck?
  5. Optimize, Make one change
  6. Measure again, Did it help? By how much? Any regressions elsewhere?

Never skip from step 1 to step 5.

For concrete profiler commands and a step-by-step run of this loop per language, see references/profiling-checklist.md.

Trade-off Framework

Every optimization trades one resource for another. Make the trade explicit.

Trade-off Example
Latency vs. throughput Batching increases throughput, raises individual latency
Memory vs. CPU Caching trades memory for fewer computations
Simplicity vs. speed Hand-rolled loops beat abstractions but obscure intent
Startup vs. runtime Lazy loading delays startup cost to first use
Bandwidth vs. latency Compression saves bandwidth, costs CPU time
Consistency vs. speed Eventual consistency is faster than strong consistency

Ask: "Which resource is scarce in this context?" Optimize for the scarce one.

Profiling Strategy

Where to Look

Start with the outermost measurement, narrow inward:

  1. End-to-end timing, Total wall-clock time for the operation
  2. Component breakdown, Which phase takes the most time?
  3. Hot path analysis, Which functions dominate the profile?
  4. Allocation analysis, Where is memory allocated and freed?

Read the full file on GitHub · 151 lines

Files

What ships with it

2 files 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. 2d ago First seen · 151 lines · 50 tokens per session scan A 0be2becab2c0

Subscribe to this mod's changes

performance is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 1,214 once invoked, about $0.0003 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