cpu-cache-opt

cpu-cache-opt is a skill for Codex from OutlineDriven/outline-driven-development. It costs 43 tokens per session (1,562 once invoked), scanned A, original, Apache-2.0.

A C++ performance guide for investigating how the processor cache affects program speed. The cache is fast memory near the processor that stores recently used data.

In plain words
What is it for?
It is for measuring cache misses, changing array or object layouts, addressing false sharing, comparing array-of-structures with structure-of-arrays, and evaluating software prefetching.
Why use it?
It replaces guesses about cache misses, false sharing, data layout, and prefetching with measurements from a reproducible workload.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for measuring cache misses, changing array or object layouts, addressing false sharing, comparing array-of-structures with structure-of-arrays, and evaluating software prefetching.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/cpu-cache-opt
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 OutlineDriven/outline-driven-development --skill cpu-cache-opt
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: 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 cpu-cache-opt

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cpu-cache-opt/github.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/cpu-cache-opt)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cpu-cache-opt"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cpu-cache-opt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cpu-cache-opt

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/cpu-cache-opt"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/cpu-cache-opt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,562 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.01562
Opus 5 $0.00022 $0.00781
Sonnet 5 $0.00009 $0.00312
Haiku 4.5 $0.00004 $0.00156

Measured 3d ago against content hash 6212fc7def7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cpu-cache-opt 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.

.devin/skills/cpu-cache-opt/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CPU cache optimization

Cache performance is a layout property before it is a code property. Measure with hardware counters, move the data so the working set fits, and re-measure. Every change must show up in the counters, or it reverts.

Contract

Field Bound contract
Trigger The task diagnoses cache misses, detects or fixes false sharing, restructures data layout, evaluates AoS versus SoA, or decides on software prefetch.
Authority Read-only. The skill runs performance tools that read the program and prints guidance; source and build changes land through the normal coding path. No remote mutation.
Side effect None beyond tool output files that the profiling tools write to their own scratch locations.
Done A measured before and after for the proposed layout change exists, with the cache counters quoted, or the diagnosis names the miss class and the evidence for it.

Inputs

  • The program and a reproducible workload: required. A benchmark that runs the hot loop long enough to fill counters.
  • The build: required, with symbols for attribution and without changing optimization between measurements.
  • The target machine: required. Counters and latencies are properties of the specific microarchitecture.

Procedure

  1. Measure before changing anything. Take the generic counters first, then the level-specific ones. Done when: a baseline of counts and miss rates for the real workload is recorded.
perf stat -e cache-references,cache-misses,cycles,instructions ./bench
perf stat -e L1-dcache-loads,L1-dcache-load-misses,LLC-loads,LLC-load-misses ./bench

Interpret relatively. An L1 miss rate that is acceptable for a pointer-chasing graph walk is severe for a streaming numeric kernel; judge each rate against the same program on the same machine, before against after, and against the memory-bound share of the run.

  1. Confirm false sharing before padding it. Threads writing to distinct variables that share one line invalidate each other constantly. The Intel HITM events count the modified-line hits that mark it. Done when: the counter either shows the traffic or rules the hypothesis out.

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 43 tokens per session scan A 6212fc7def7e

Subscribe to this mod's changes

cpu-cache-opt is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,562 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 2026-09-06.

Related

Other skills, from other repositories

memory-safety-patterns

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.

rmyndharis/antigravity-skills · 45 tokens

cpp

Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics. Use for: C/C++ questions, C/C++ interview preparation, modern language features, RAII/memory management, templates/generics, CUDA…

crazyguitar/cppcheatsheet · 0 tokens

cpp-debugging

Use when a C++ failure involves memory lifetime, undefined behavior, native crashes, or debugger-only state — debug with symbols, sanitizers, and platform-native debuggers before patching symptoms.

drvoss/everything-copilot-cli · 42 tokens

memory-safety-patterns

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.

RudyCity/superagent · 45 tokens

gcc

GCC compiler skill for C/C++ projects. Use when selecting optimization levels, warning flags, debug builds, LTO, sanitizer instrumentation, or diagnosing compilation errors with GCC. Covers flag selection for debug vs release, ABI concerns, preprocessor macros, profile-guided optimization, and integration with build…

mohitmishra786/low-level-dev-skills · 85 tokens

cuopt-developer

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

NVIDIA/skills · 47 tokens