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 2233admin/performance-patterns-skill --skill performance-patternsgit clone --depth 1 https://github.com/2233admin/performance-patterns-skillWrote 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/2233admin/performance-patterns-skill/performance-patterns)<a href="https://agentmods.dev/skills/2233admin/performance-patterns-skill/performance-patterns"><img src="https://agentmods.dev/badge/skills/2233admin/performance-patterns-skill/performance-patterns/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/2233admin/performance-patterns-skill/performance-patterns"><img src="https://agentmods.dev/badge/skills/2233admin/performance-patterns-skill/performance-patterns.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00213 | $0.01519 |
| Opus 5.5 | $0.00085 | $0.00608 |
| Sonnet 5.5 | $0.00043 | $0.00304 |
| Haiku 4.5 | $0.00021 | $0.00152 |
Grade A, and why
performance-patterns 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance patterns skill
A growing catalog of well-known code patterns that cause performance problems, with detection signals and resolution playbooks for each. The core pattern catalog focuses on x86 CPU code, with platform routing for Windows, WSL Linux, native Linux, and CUDA/NVIDIA environments.
The optimization knowledge is portable where the hardware is the same. What changes by platform is the mechanics: profiler vocabulary, compiler flags, debug-info format, synchronization primitives, CPU feature detection, and whether the bottleneck is CPU host code or CUDA device work.
Step 0 — Route the platform
If the user mentions WSL, Linux, CUDA, NVIDIA, GPU, Nsight, driver/toolkit
mismatch, containers, or the platform is unclear, read
references/platform-routing.md first.
Then load the platform-specific reference:
| Platform / symptom | Read |
|---|---|
| Windows native C/C++ CPU performance | PORTING-NOTES.md |
| WSL Linux CPU performance | references/wsl-linux.md, then references/linux-native.md |
| Native Linux CPU performance | references/linux-native.md |
| CUDA/NVIDIA setup or GPU performance | references/cuda.md |
Use scripts/collect-perf-env.ps1 on Windows and
scripts/collect-perf-env.sh inside WSL/native Linux when the environment is
the problem or the user has not provided enough toolchain/profiler context.
How to use this skill
Step 1 — Load the right file for your context
| Context | Read this file |
|---|---|
| You have profiling output (VTune, AMD uProf, ETW/WPA, perf, flamegraph, Nsight summary, etc.) | triggers/from-profile.md |
| You are reading existing source code and have no profiling data yet | triggers/from-source.md |
| You are writing new performance-sensitive C/C++ or SIMD code | guidelines/new-code.md |
The trigger files cover all the same patterns; they are separated so you only
load what is relevant. guidelines/new-code.md is a write-time checklist —
load it instead of a trigger file when generating new code, not reviewing it.
What ships with it
37 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.
- agents/openai.yaml 218 B
- design.md 7.6 KB
- guidelines/new-code.md 9.5 KB
- library/cpu-dispatch.md 8.6 KB
- library/crc32c_avx512_vpclmulqdq.c 5.5 KB
- library/crc32c_portable.c 4.0 KB
- library/crc32c_sse42.c 3.5 KB
- patterns/cold-path-annotation.md 6.9 KB
- patterns/cv-thundering-herd.md 9.5 KB
- patterns/false-sharing.md 6.5 KB
- patterns/fast-crc32c-impl.md 5.3 KB
- patterns/fast-crc32c.md 3.1 KB
- patterns/library-version-upgrade.md 4.1 KB
- patterns/missing-restrict.md 6.6 KB
- patterns/missing-vzeroupper.md 6.9 KB
- patterns/mutex-to-rwlock.md 7.0 KB
- patterns/parallel-accumulator.md 8.6 KB
- patterns/per-cpu-stats.md 11 KB
- patterns/simd-sort.md 7.3 KB
- patterns/simd-upconversion-impl.md 26 KB
- patterns/simd-upconversion.md 10.0 KB
- patterns/tests/mutex-to-rwlock-bench.c 7.8 KB
- patterns/tests/mutex-to-rwlock-results.md 2.7 KB
- patterns/tests/run-mutex-to-rwlock-bench.ps1 1.6 KB runs code
- patterns/ttas.md 5.4 KB
- PORTING-NOTES.md 11 KB
- references/cuda.md 2.7 KB
- references/known-algorithms-impl.md 7.6 KB
- references/known-algorithms.md 931 B
- references/library-versions.md 4.5 KB
- references/linux-native.md 1.7 KB
- references/platform-routing.md 2.5 KB
- references/wsl-linux.md 1.4 KB
- scripts/collect-perf-env.ps1 3.2 KB runs code
- scripts/collect-perf-env.sh 1.5 KB runs code
- triggers/from-profile.md 12 KB
- triggers/from-source.md 13 KB
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.
- 1mo ago First seen · 129 lines · 213 tokens per session scan A 03def9e54eb6
performance-patterns is a skill published in the GitHub repository 2233admin/performance-patterns-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 213 tokens to every session and 1,519 once invoked, about $0.0009 per session on Opus 5.5. 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
linux-phone-porting
Use for every hardware bring-up or debug session that ports mainline Linux to a phone or tablet. Retail-unlock targets require an already-unlocked bootloader; locked retail bootloaders are out of scope. Exploit-booted and firmware-booted targets require a demonstrated boot path; the skill never provides unlock or…
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
agentsop-prompt-history-inspect
Tool skill — the first move in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got…
perf-analyze
Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill), nsys + ncu per-kernel…
agentsight-bugfix
A five-stage workflow for fixing bugs in AgentSight: understand the report, reproduce the problem, find its cause, make a small code change, and verify the result. AgentSight is a system that observes and analyses agent activity.
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…