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 agentmods add skills/sisibeloved/cpython-optimize-skill/pyperformance-result-comparenpx skills add sisibeloved/cpython-optimize-skill --skill pyperformance-result-comparegit clone --depth 1 https://github.com/sisibeloved/cpython-optimize-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/sisibeloved/cpython-optimize-skill/pyperformance-result-compare)<a href="https://agentmods.dev/skills/sisibeloved/cpython-optimize-skill/pyperformance-result-compare"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/pyperformance-result-compare.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 | $0.00042 | $0.00618 |
| Opus 5 | $0.00021 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
pyperformance-result-compare 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.
What it actually says
pyperformance Result Compare
负责解释结果，不负责跑 benchmark。
输入
- baseline
run.json - candidate
run.json speedup.json- 提交 baseline / candidate commit
- 口径 baseline：CPython JIT、CinderX JIT、解释执行等
判断
- 命令口径是否一致
- 按
../using-cpython-optimize/references/baseline-source-contract.md核对 baseline source 是否baseline_source_verified，包括口径 baseline、提交 baseline、source path、commit/ref、dirty 状态、patchlevel.h、SOABI和容器 bind mount。 - 按
../using-cpython-optimize/references/pyperformance-affinity-guidance.md核对 baseline/candidate 的原始/实际--affinity、可用 CPU 映射和并行/串行口径是否一致。 - 先按
../using-cpython-optimize/references/pyperformance-env-contract.md核对 baseline/candidate 的--inherit-environ、driver/worker env 和唯一差异轴。 - CinderX JIT 口径必须核对 worker 内证据：
.pth、pyvenv.cfg/include-system-site-packages、import cinderx/_cinderx、cinderx.__file__、cinderx.get_import_error()、cinderx.is_initialized()。 - baseline/candidate 是否只在目标变量上不同
- 方差、噪声和异常值
- 收益范围、无收益范围、未验证范围
- 需要回到
pyperformance-worker-run的异常用例 - 如果 baseline source、affinity 口径、环境契约、worker JIT 证据缺失或 baseline/candidate 不一致，先降级结论，不把
run.json写成可信性能收益。
反问 Gate
- baseline/candidate
run.json、speedup.json或口径 baseline 缺失且无法从路径/文件推断时，询问用户。 - baseline source 缺少 commit/ref、dirty 状态、source path 或用户指定事实源时，询问用户补充 baseline 事实源。
- 方差或异常值使结论不稳定，需要补跑、扩大样本或降级结论时，询问。
- 用户要求收益外推到全量，但当前只覆盖单 benchmark 或小集合时，询问是否晋级验证。
输出可信收益、可信回归、baseline source 状态、噪声项、补测建议和不能外推的范围。
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 · 39 lines · 42 tokens per session scan A 7e5167eedc76
pyperformance-result-compare is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 618 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…