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/compiler-optimization-theorynpx skills add sisibeloved/cpython-optimize-skill --skill compiler-optimization-theorygit 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 | $0.00112 | $0.01260 |
| Opus 5 | $0.00056 | $0.00630 |
| Sonnet 5 | $0.00022 | $0.00252 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
compiler-optimization-theory 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compiler Optimization Theory
编译器中后端理论背景，供理解与评估 CinderX 的 IR、优化、调度、寄存器分配设计。
是"读后内化"型知识，与 isa-instruction-lookup（查规格）分工不同：
这里回答"为什么这样设计、有哪些方案、取舍是什么"，不回答"某指令编码是什么"。
来源声明
基于 Cooper & Torczon《Engineering a Compiler》2nd edition（Elsevier 2012） PDF 逐章校对的概念提炼，引用到小节级（各 reference 头部标注 PDF 页码， 印刷页 ≈ PDF−25）。算法细节以该书为准。 linear scan / PBQP 不在本书 2e 正文，相关条目已单独标注原始文献出处。
何时读哪个
| 问题形态 | 读 |
|---|---|
| HIR/LIR 为什么分层？SSA 有什么好处？IR 设计的取舍轴？ | references/intermediate-representations.md |
| 某优化 pass 在做什么、为什么有效、pass 顺序怎么排？ | references/optimization-fundamentals.md |
| 机器码为什么这样排？延迟/占用率怎么权衡？循环怎么调度？ | references/instruction-scheduling.md |
| spill 为什么发生？图着色 vs 线性扫描？move elimination？ | references/register-allocation.md |
与现有技能的衔接
- 读 CinderX HIR/LIR dump 时：
cinderx-hir-lir-analyze负责取证据，本技能提供 "这段 IR 形态说明编译器在做什么"的理论判读框架。 - 评审 JIT 改动时：
cinderx-jit-review负责正确性风险清单，本技能帮助判断 "这个优化在编译理论上的前置条件是否满足"。 - 涉及具体指令行为/编码：一律转
isa-instruction-lookup查库，本技能不覆盖。
理论 → 查证 硬规则（不可跳过）
本技能只回答"为什么这样设计、有哪些方案、取舍是什么"。分析中一旦落到具体指令，
必须按"查证问题"调 isa-reference MCP。查证主体是语义与用法，不是分类和
feature：category 只用于同名消歧（ABS 三域），filter_by_environment 只在
环境部署判定时用——优化替换经常跨 category、跨 feature 域（base 需求用
SIMD 指令满足、SVE 指令替换 base 序列都合法），候选检索不得被分类过滤。
| 查证问题 | 怎么查（工具 + 必做的比对动作） |
|---|---|
| 语义核对：方案假设指令做 X（如"CSEL 无条件写 Rd"），它真的做 X 吗 | lookup_instruction(mnemonic, verbose=True) → 逐条读 operation_pseudocode 与方案的语义假设比对；不一致即方案错误，不得当备注带过 |
| 用法核对：这条汇编/lowering 写法合法吗、有什么编码陷阱 | 同上 verbose → 核对 asm_templates（合法语法形态）与 operand_docs（操作数约束：宽度限制、内存源语义、编码位要求）——陷阱在这里暴露（如 CMOVcc 不支持 8-bit 目的、内存源被无条件读） |
| 更优写法发现：有没有语义一致但更高效的替换 | 按语义检索候选：find_instruction_by_function + optimization-intent-map.md（跨 category/feature 不设限）→ 每个候选取伪代码比对语义一致 → 比较指令数/依赖链/副作用；微架构收益须 perf 证据 |
| 环境部署判定（仅在确认目标机器支持时） | filter_by_environment(env_features)，feature 列表来自环境审计 |
判据：方案对指令行为的每条语义假设，必须能在该指令 operation_pseudocode
里指出对应行；用法断言必须对应 asm_templates/operand_docs 条目。
只回答"某指令是 base 类、无 feature 依赖"不构成查证——那只是可用性，
回答不了"语义符不符、用法对不对、有没有更优写法"。
What ships with it
4 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.
- 2d ago First seen · 61 lines · 112 tokens per session scan A a33859928234
compiler-optimization-theory is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,260 once invoked, about $0.0006 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…