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 sisibeloved/cpython-optimize-skill --skill cinderx-interpreter-case-analyzegit 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/cinderx-interpreter-case-analyze)<a href="https://agentmods.dev/skills/sisibeloved/cpython-optimize-skill/cinderx-interpreter-case-analyze"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/cinderx-interpreter-case-analyze.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 5.1 | $0.00064 | $0.01042 |
| Opus 5 | $0.00032 | $0.00521 |
| Sonnet 5 | $0.00013 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
cinderx-interpreter-case-analyze 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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CinderX Interpreter Case Analyze
解释执行用例 / 非 JIT 用例不能硬套 HIR/LIR 结论。先证明 benchmark 本体未进入 CinderX JIT gate，或性能差距主要来自解释执行、gate 拒绝、运行时开销和 AutoJIT 分类决策，再做阶段分析。
前置证据
- 真实 pyperformance worker 命令和环境契约。
cinderx-jit-entry-check的entered_cinderx_jit=false，或目标热函数未进入 gate 的证据。- CPython JIT baseline、CinderX JIT 优化前、CinderX JIT 优化后的配对结果。
- perf、计数器、worker log、gate log、函数级调用次数或其它穿刺证据。
穿刺证据
穿刺证据必须把总耗时拆到可行动阶段，不能只写 speedup 结论。至少覆盖：
| 阶段 | 证据 |
|---|---|
| worker / benchmark 本体 | 真实 worker 命令、输入规模、warmup/loops、affinity、环境变量 |
| CPython JIT baseline | 基线结果、热点、JIT 状态、函数级证据 |
| CinderX JIT 优化前 | 优化前结果、gate / AutoJIT 状态、解释执行热点 |
| CinderX JIT 优化后 | 优化后结果、已改变阶段、残留热点 |
| 差距归因 | 哪些阶段贡献 gap，哪些阶段已被优化，哪些仍可优化 |
分阶段平铺表
输出一张平铺表，列必须包含：
| 阶段 | CPython JIT baseline | CinderX JIT 优化前 | gap | CinderX JIT 优化后 | 已优化量 | 剩余 gap | 证据 | 下一步 |
|---|
要求：
- 每行只放一个阶段或一个可验证子阶段。
gap、已优化量、剩余 gap要有数值、比例或明确的定性证据。- 不能把多个阶段揉成“解释器慢”一类结论。
- 没有证据的行标记为待补证据，不得当作根因。
函数形状表
分阶段平铺表之后，必须给函数形状表。基于 autojit 分类模型列出全量函数形状和 gate 策略，不只挑热点函数。
| 函数 | 模块/路径 | 调用/热度 | bytecode 形状 | 动态特性 | AutoJIT 分类 | gate 策略 | gate 结果 | 证据 |
|---|
函数形状至少覆盖：
- loop、分支、异常处理、generator/coroutine、closure、globals、locals/freevars/cellvars。
- call 形态：Python call、C API、method/descriptor、vectorcall、dynamic dispatch。
- 数据形态：dict/list/tuple、attribute access、boxing/unboxing、type stability。
- AutoJIT 分类：可编译、待观察、拒绝、低收益、风险高、证据不足。
- gate 策略：阈值、白名单/黑名单、函数形状规则、平台规则、实验开关。
不进入 gate 的阶段详细拆解
只要有函数不进入 gate，就追加阶段详细拆解：
- 发现：函数如何被发现，调用次数和热度是什么。
- 分类：autojit 分类模型给出的函数形状和风险。
- gate：命中哪条 gate 策略、阈值或拒绝规则。
- 拒绝：不进入 gate 的直接原因。
- fallback：解释执行 fallback 后落在哪些运行时阶段。
- 代价：该拒绝对 CPython JIT baseline vs CinderX JIT 优化前 gap 的贡献。
- 行动：调 gate、改函数形状支持、降低运行时开销或放弃优化的下一步。
输出
返回穿刺证据、分阶段平铺表、函数形状表、每个不进入 gate 函数的阶段详细拆解、已优化量、剩余 gap、风险和最小验证命令。
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.
- 7d ago First seen · 71 lines · 64 tokens per session scan A ed562e56d584
cinderx-interpreter-case-analyze is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 1,042 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…