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-jit-reviewgit 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-jit-review)<a href="https://agentmods.dev/skills/sisibeloved/cpython-optimize-skill/cinderx-jit-review"><img src="https://agentmods.dev/badge/skills/sisibeloved/cpython-optimize-skill/cinderx-jit-review.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 | $0.00105 | $0.01446 |
| Opus 5 | $0.00053 | $0.00723 |
| Sonnet 5 | $0.00021 | $0.00289 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
cinderx-jit-review 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CinderX JIT Review
定位
对 CinderX JIT PR 做 correctness-first code review。优先找会改变 Python 语义、JIT 层级契约、exception edge、deopt/refcount、specialized opcode 消费、helper fallback 或验证边界的风险。
这个 skill 不是性能调优流程。性能收益只能作为背景；review 结论先回答“这次 JIT 改动如何证明没有改坏语义”。
必读材料
每次完整 review 前读取：
references/jit-correctness-validation-strategy.md：分层正确性策略、may-raise / exception table、RuntimeTests 硬要求。references/review-checklists.md：按风险类型检查 helper、deopt、refcount、adaptive opcode、side effect、AArch64 codegen 和覆盖证据。
如果只回答一个局部问题，也至少读取对应 reference 中的相关小节；不要只凭通用 C++ 或 Python 经验下结论。
开放性原则
把本 skill 当作 review 下限，不当作风险全集。先从具体 diff、调用链、执行时机、异常边、ownership、平台约束和测试证据出发，再用 references 补充已知高风险模式。
- 如果 diff 暴露了 references 没列出的新风险，也要按 correctness-first review 输出 finding。
- 不要因为某个问题不属于 may-raise、deopt、refcount、adaptive opcode 或 AArch64 checklist，就跳过它。
- 当新风险反复出现时，在 review 结束后建议把它沉淀回
references/review-checklists.md，但不要等文档更新后才指出问题。 - 明确区分“本 skill 没覆盖”和“这个 PR 没风险”；前者不能推出后者。
Review 顺序
-
明确 review 对象。
- 确认 repo、base/head、PR/MR 编号、diff 范围和目标分支。
- 如果是 GitCode PR，优先 review
refs/merge-requests/<id>/head和refs/merge-requests/<id>/merge，不要只看分支 tip。
-
判定改动层级。
- Bytecode builder / preload。
- HIR lowering、optimization pass、guard、verifier。
- LIR、regalloc、uop。
- Codegen、AArch64 backend、runtime helper。
- Deopt、FrameState、frame layout、live refs。
- RuntimeTests、
test_cinderx、test_kunpeng、gate/tooling。
-
写出本次 correctness contract。
- 这次优化依赖的 Python 语义前提是什么？
- 哪些前提由 guard、verifier、helper contract 或 codegen invariant 保护？
- 前提失效时如何 fallback、deopt 或回到解释器语义？
- 哪些机器检查证明 fast path 命中、fallback 正确、JIT on/off 等价？
-
按风险 checklist 做第二遍 review。
may-raise点是否被新增、删除、移动、合并或替换？- 是否消费 CPython adaptive / specialized opcode 或 inline cache？
- 是否改变 helper call、side-effect 顺序、container mutation、attribute access、descriptor 行为？
- 是否改变 borrowed / owned ref、refcount insertion 输入、deopt live refs？
- 是否改变 AArch64 寄存器、NZCV flags、W/X 宽度、SP alignment、branch/code patching、deopt mapping？
What ships with it
2 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.
- 7d ago First seen · 100 lines · 105 tokens per session scan A ba351c440cb1
cinderx-jit-review is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 9d ago), licensed MIT. It adds 105 tokens to every session and 1,446 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…