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/validation-strategynpx skills add sisibeloved/cpython-optimize-skill --skill validation-strategygit 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 | $0.00049 | $0.00916 |
| Opus 5 | $0.00024 | $0.00458 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
validation-strategy 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
验证策略：准确与高效
目标
把“验证”拆成可晋级的阶梯。准确来自证据门禁，高效来自成本预算、缓存复用和禁止过早全量验证。
验证阶梯
| 等级 | 名称 | 用途 | 典型产物 |
|---|---|---|---|
| L0 | L0 静态审计 | 不运行或少运行，先查环境、配置、代码、ISA、命令口径 | 环境表、候选路径、风险清单 |
| L1 | L1 最小功能验证 | 证明改动或环境没有明显错 | import、smoke、单元测试、最小用例 |
| L2 | L2 单 benchmark 复现 | 用目标用例复现性能/崩溃/热点 | 单 benchmark 数据、HIR、perf、gdb |
| L3 | L3 小集合验证 | 验证收益或风险是否扩散到相关用例 | 相关 Runtime/pyperformance 子集 |
| L4 | L4 全量验证 | 发布、提交、报告前的最终信心 | 全量 Runtime、全量 pyperformance、聚合报告 |
禁止默认跳到 L4。近千条 RuntimeTests 功能测试和近三小时 pyperformance 性能测试全量是晋级验证，不是调试循环默认动作。
晋级规则
- L0 没有明确环境和命令口径时，不进入性能结论。
- L1 没有通过时，不讨论性能收益。
- L2 没有复现目标现象时，不实施面向该现象的优化。
- L3 只覆盖预期受影响集合；不要把小集合结论外推到全量。
- L4 只在准备提交、报告、扩大收益声明或用户明确要求时运行。
每次晋级前写清：
- 当前验证等级
- 预计耗时和资源
- 命令、日志和产物路径
- 失败后的下一步
- 为什么需要更高等级
成本预算
高成本动作必须先问“是否可避免或复用”：
| 高成本动作 | 优先替代 |
|---|---|
| 在线安装依赖 | 复用 wheel/cache、镜像源、已有容器 |
| 编译 CinderX | 判断改动是否影响 C/C++/JIT codegen，再增量构建 |
| 全量 Runtime | 先跑相关目录、失败用例、smoke 子集 |
| 全量 pyperformance | 先跑目标 benchmark、相关小集合、历史异常集合 |
复用缓存是默认策略：容器镜像、pip cache、build 目录、benchmark 结果和日志都应优先复查再重跑。
反问 Gate
- 用户未明确授权 L3/L4、全量 Runtime、全量 pyperformance、在线安装依赖或 CinderX 编译时，先给预计耗时和替代方案并询问。
- 无法判断继续等待、复用缓存、换镜像、降级验证还是中止时，必须询问。
- 用户同时要求“最快”和“正式结论”，但证据等级不足以支撑正式结论时，询问优先级。
证据要求
准确结论至少包含：
- 环境证据：Python、编译器、CinderX commit、容器线、关键变量
- 命令证据：真实命令、stdout/stderr、exit status、产物路径
- 功能证据：相关测试或最小用例
- 性能证据：口径、baseline 含义、样本/方差或可解释的单用例数据
- 根因证据：热点、HIR/LIR/机器码、perf/gdb 或明确排除项
没有证据时只能写“假设”，不能写“根因”。
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 · 68 lines · 49 tokens per session scan A 3035d5927dec
validation-strategy is a skill published in the GitHub repository sisibeloved/cpython-optimize-skill (2 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 916 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.