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 OutlineDriven/outline-driven-development --skill cpu-cache-optgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/cpu-cache-opt)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01562 |
| Opus 5 | $0.00022 | $0.00781 |
| Sonnet 5 | $0.00009 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
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.
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
- 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.
- 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.
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.
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.
- 3d ago First seen · 110 lines · 43 tokens per session scan A 6212fc7def7e
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.
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.
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…
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.
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.
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…
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.