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 laolaoshiren/claude-code-skills-zh --skill perf-profilergit clone --depth 1 https://github.com/laolaoshiren/claude-code-skills-zhWrote 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/laolaoshiren/claude-code-skills-zh/perf-profiler)<a href="https://agentmods.dev/skills/laolaoshiren/claude-code-skills-zh/perf-profiler"><img src="https://agentmods.dev/badge/skills/laolaoshiren/claude-code-skills-zh/perf-profiler/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/laolaoshiren/claude-code-skills-zh/perf-profiler"><img src="https://agentmods.dev/badge/skills/laolaoshiren/claude-code-skills-zh/perf-profiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.00960 |
| Opus 5 | $0.00039 | $0.00480 |
| Sonnet 5 | $0.00016 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
perf-profiler 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 12d 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
性能分析助手
工作流程
1. 明确目标与边界
先确认或从项目中核实:
- 目标指标,如延迟、吞吐量、CPU、内存、查询次数或包体积。
- 可复现的场景、数据规模、运行环境、版本和关键配置。
- 用户允许分析和修改的范围,以及是否可以运行负载或 profiler。
没有明确目标时,先用现有监控、benchmark 或用户现象缩小范围,不把“代码看起来慢”当成瓶颈结论。
2. 建立基线
优先复用项目已有的启动、benchmark、trace 和 profiling 配置。在相同环境、数据和负载下记录:
- 预热方式、并发度、重复次数和统计口径。
- 代码版本、依赖版本及影响结果的配置。
- 原始测量值和波动范围;条件允许时保留机器可读结果。
无法运行项目时,只能进行静态分析,并把发现标为“待验证候选”。
3. 收集证据
按技术栈选择 profiler、trace、火焰图、查询计划、网络时序或内存快照,定位时间或资源实际消耗的位置。常见维度包括:
- 代码:算法复杂度、重复计算、分配热点、同步阻塞和并发争用。
- 数据库:N+1 查询、扫描量、索引使用、锁等待和连接池状态。
- 网络:请求瀑布、有效载荷、压缩、缓存命中和外部服务延迟。
复杂度分析和代码审查只能证明风险,不能单独证明运行时影响。
4. 提出最小改动
- 将建议绑定到具体证据、文件或调用链。
- 说明正确性、内存、吞吐量、维护成本和兼容性方面的权衡。
- 优先处理证据最强、影响最大的热点;不同时改动多个无法独立归因的因素。
- 为代码、配置和数据结构变更准备验证与回滚方式。
5. 同条件复测
修改后使用与基线一致的环境、数据、负载、预热和统计口径复测,并运行受影响功能的正确性测试。报告原始结果、波动、差异和尚未控制的变量。
只有真实完成同条件测量后,才能写耗时、百分比或“已改善”等确定性结论。
证据等级
- 已测量:有可复现基线、profiling 证据和实际结果。
- 静态推断:由复杂度、调用关系或配置推导出的候选问题,尚未实测。
- 待验证:缺少环境、数据或权限,当前无法判断影响。
安全与授权边界
- 默认只在本地或用户明确指定的测试环境进行只读分析。
- 生产环境 profiling、压测、
EXPLAIN ANALYZE及索引、缓存、连接池、CDN 或外部服务配置变更必须获得明确授权。 - 不在报告中暴露生产数据、凭据或含敏感信息的 profiling 产物。
- 不为得到漂亮数字而删除正确性检查、降低数据规模或改变统计口径。
- Windows 与 Linux 优先使用项目已有工具;平台特定命令需说明适用范围或提供等价方法。
输出
## 性能分析结果
- 目标指标与场景:
- 环境、版本与数据规模:
- 基线与测量方法:
## 发现
| 证据等级 | 位置 | 证据 | 影响与限制 |
|----------|------|------|------------|
## 改动与权衡
## 同条件复测
- 正确性验证:
- 性能结果:
- 未控制变量与待验证项:
- 回滚方式:
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.
- 12d ago First seen · 90 lines · 78 tokens per session scan A d21507472702
perf-profiler is a skill published in the GitHub repository laolaoshiren/claude-code-skills-zh (836 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 960 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
postmortem-solo
Run a lightweight, blame-free postmortem after an incident, failed launch, or missed deadline — for one person. Use when the user says "that didn't go well", "the launch flopped", "we had an outage", "I missed my deadline", or wants to learn from a recent failure.
bug-from-user
Convert a vague user complaint into a reproducible bug report a solo dev can act on. Use when the user pastes a confusing customer message, says "user says it's broken but I can't repro", "this email makes no sense", or wants to triage a bug report.
tool-calling-tutor
Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…