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-stat-reportnpx skills add sisibeloved/cpython-optimize-skill --skill pyperformance-stat-reportgit clone --depth 1 https://github.com/sisibeloved/cpython-optimize-skillWhat 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 | $0.00048 | $0.00744 |
| Opus 5 | $0.00024 | $0.00372 |
| Sonnet 5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
pyperformance-stat-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
pyperformance Stat Report
负责把已存在的 pyperformance JSON 结果整理成适合人工阅读和汇报的统计产物。此 skill 只读结果，不负责跑 benchmark，也不能替代 pyperformance-result-compare 对 baseline source、CPU affinity、worker env、噪声和可信度的判断。
CinderX/JIT 性能结论必须先确认结果满足 ../using-cpython-optimize/references/pyperformance-env-contract.md；get_stat.py 只格式化已有数据。
输入
- 两个或更多
run.json/ pyperformance JSON 文件，按对比顺序传入。 - 第一个 JSON 是 ratio 计算的 baseline。
- 可选 benchmark 名称，用于只输出指定用例。
脚本
从已加载 skill 的目录解析 bundled helper 绝对路径，不要假设当前目录是插件根目录。保持报告输出目录为 working directory：
SKILL_DIR="/absolute/path/from-loaded-skill/pyperformance-stat-report"
SCRIPT="$SKILL_DIR/scripts/get_stat.py"
cd <report-output-directory>
python "$SCRIPT" [-c] [-b <benchmark>]... <baseline.json> <candidate.json> [more.json ...]
JSON 可以使用绝对路径，也可以使用相对报告目录的路径。未传 JSON 时脚本会扫描当前目录 *.json；正式报告中优先写显式路径。
模式
-c/--console-only：只打印对比表，不生成文件，不需要openpyxl或matplotlib。- 默认模式：打印表格，在临时目录生成完整报告后统一发布
benchmark_comparison.xlsx和benchmark_trends_part<N>.png；生成失败时保留上一套完整报告。 -b/--benchmarks：只保留指定的公共 benchmark；每个 benchmark 单独写一个-b，例如-b 2to3 -b chaos，并保持用户给定顺序。
默认产物模式需要：
python -m pip install openpyxl matplotlib
语义
- 只比较所有有效 JSON 共有的 benchmark。
- 第一个 JSON 必须成功加载且包含 benchmark；除 baseline 外还必须至少有一个有效 candidate。
- 拒绝通过等价路径、符号链接或硬链接重复传入同一物理 JSON，避免自比较报告。
- 单项 ratio 和几何平均都使用
baseline_time / current_time。 - ratio 大于
1.0表示快于第一个 JSON；小于1.0表示慢于第一个 JSON。 - 显示单位按 baseline 文件中该 benchmark 的耗时量级选择。
输出要求
使用此 skill 时必须输出：
- 真实命令和 working directory；
- JSON 顺序，以及哪个文件是 baseline；
- benchmark filter（如使用）；
- 公共 benchmark 数量；
- 生成的
benchmark_comparison.xlsx/benchmark_trends_part<N>.png路径，或说明使用了--console-only； - 被跳过的 JSON 或未命中的指定 benchmark。
What ships with it
1 file 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.
- 2d ago First seen · 62 lines · 48 tokens per session scan A eea29825f386
pyperformance-stat-report is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 744 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.