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/using-cpython-optimizenpx skills add sisibeloved/cpython-optimize-skill --skill using-cpython-optimizegit 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 | $0.00056 | $0.01385 |
| Opus 5 | $0.00028 | $0.00692 |
| Sonnet 5 | $0.00011 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
using-cpython-optimize 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPython/CinderX Optimize Router
薄 router：Orchestrator 选 Workflow，Workflow 分派 Agent，Agent 调专业 Skill。
层级
| 层 | 职责 |
|---|---|
| Orchestrator | 运行时主 Agent，理解目标、选 Workflow、分派 Agent、合并结果 |
| Workflow | 端到端剧本和 gate |
| Agent | 阶段负责人，接管环境、跑分、crash、JIT 或平台分析 |
| Skill | CPython/CinderX 专业动作 |
Agent 路由
Agent 文档不是原生 Skill 自动触发单元。主 Agent 或 hook 一旦决定分派某个 Agent，必须按 agents/<agent>.md 路径显式读取对应角色文档，再执行其职责、反问 Gate 和输出要求。
| Agent | 触发 |
|---|---|
cinderx-orchestrator |
任意入口和任务分发 |
cinderx-environment-verifier / environment-verifier |
环境审计、三态判断 |
pyperformance-baseline-runner / baseline-runner |
baseline slot 跑分 |
pyperformance-candidate-runner / candidate-runner |
candidate slot 跑分 |
pyperformance-benchmark-analyst |
run.json / speedup.json 结果解读 |
cinderx-crash-triager / crash-triager |
SIGSEGV、exit 139、core dump |
cinderx-jit-analyst |
CinderX JIT、HIR/LIR、解释执行用例、机器码优化点 |
cinderx-platform-analyst |
Kunpeng/x86、ISA、微架构差异 |
cinderx-evidence-analyst |
单用例证据表、跨层根因下钻、穿刺判读 |
反问 Gate
能从仓库、环境、日志或历史产物查证的信息先查证，不问用户。以下信息无法唯一确定时必须暂停反问：
| 缺口 | 典型问题 |
|---|---|
| 目标路线 | 三个主 Workflow、supporting workflow 或验证等级无法唯一选择 |
| 实验轴 | benchmark、平台、baseline/candidate、JIT 口径或环境句柄缺失 |
| 高成本动作 | 清理环境、bootstrap、在线安装、编译 CinderX、全量 Runtime、全量 pyperformance |
| 运行中异常 | 远端无输出、timeout、网络卡顿时需要继续等待、换镜像、复用缓存或中止 |
| 证据链断裂 | crash 缺真实命令/core，结果比较缺配对 run.json，平台分析缺平台对 |
平台映射：Codex 优先用 request_user_input，Claude Code 优先用 AskUserQuestion；工具不可用时，退化为普通文本选择题并等待用户回答。
需要结构化选项时读取 references/clarifying-question-templates.md，复用其中的 question_id、选项和文本降级格式。
Environment Verifier 三态
| 状态 | 下一步 |
|---|---|
可复用 / reusable |
返回环境句柄 |
新环境 / needs_bootstrap |
调 cinderx-env-bootstrap |
被破坏 / needs_clean_bootstrap |
调 cinderx-env-clean 再 bootstrap |
专业 Skill
cinderx-env-validate、cinderx-env-clean、cinderx-env-bootstrap、cinderx-remote-lab-ops、cinderx-ab-run-slot、cpython-runtime-test-run、cinderx-smoke-check、pyperformance-worker-run、pyperformance-suite-run、pyperformance-result-compare、pyperformance-stat-report、cinderx-gdb-core-triage、cinderx-hir-dump、cinderx-jit-entry-check、cinderx-hir-lir-analyze、cinderx-interpreter-case-analyze、cinderx-isa-microarch-compare、cinderx-evidence-table、cinderx-optimization-report、validation-strategy、isa-instruction-lookup、compiler-optimization-theory。
What ships with it
5 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.
- yesterday First seen · 82 lines · 56 tokens per session scan A d3c6e00c1482
using-cpython-optimize is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 1,385 once invoked, about $0.0003 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…