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 lovelyXiaoQi/mcdk-mcp-tracy --skill mcdk-tracy-profilinggit clone --depth 1 https://github.com/lovelyXiaoQi/mcdk-mcp-tracyWrote 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/lovelyxiaoqi/mcdk-mcp-tracy/mcdk-tracy-profiling)<a href="https://agentmods.dev/skills/lovelyxiaoqi/mcdk-mcp-tracy/mcdk-tracy-profiling"><img src="https://agentmods.dev/badge/skills/lovelyxiaoqi/mcdk-mcp-tracy/mcdk-tracy-profiling/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/lovelyxiaoqi/mcdk-mcp-tracy/mcdk-tracy-profiling"><img src="https://agentmods.dev/badge/skills/lovelyxiaoqi/mcdk-mcp-tracy/mcdk-tracy-profiling.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.02456 |
| Opus 5 | $0.00046 | $0.01228 |
| Sonnet 5 | $0.00018 | $0.00491 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
mcdk-tracy-profiling 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCDK Tracy 性能监测工作流
mcdk-mcp-tracy 从游戏内嵌的原生 Tracy server(TCP 8086)抓一小段 trace,归约成每个函数的耗时排行(self / total / calls),配合前后 diff 量化优化收益。原始数据在服务端归约,agent 只看 top-N 与 diff。
前置条件
- 游戏在运行,原生 Tracy server 监听 8086(通过MCDK/MCStudio启动的ModPC均可)。
bin/tracy-capture.exe、bin/tracy-csvexport.exe存在,版本与游戏内嵌 Tracy 一致(当前 v0.11.1)。- 仅
tracy_jank_fps需要游戏由mcdk.exe启动且.mcdev.json的mcp_server_config.enabled=true;函数耗时抓取不经 MCDK。
核心原则
- 先探针后采样:
tracy_status确认native_tracy.reachable=true、bin_present=true再动手。 - 采样前先和用户对齐时长与场景:负载要用户亲自在游戏里触发,约定好了、用户就位了再开采(见推荐流程第 2 步)。
- 采样窗口内制造真实负载:让游戏跑代表性玩法;Tracy 只记录窗口内实际执行的 zone,静止难以抓取性能高消耗的部分。
- 用
name_contains聚焦 MOD:函数显示为"函数名 @ 源文件",按脚本包前缀(如MyModScripts)过滤;过滤只影响 inline 返回,全量仍存进 capture。 - 结论用 diff 说话:优化前后各采一次、打不同
label,tracy_diff_captures量化收益,不凭感觉。 - 改代码前必须用户拍板:先交热点报告 + 优化计划(见下),用户选了哪条才改哪条,不要未经确认就动代码。
推荐流程
tracy_status()—— 失败看reason/hint(8086 不可达 → 游戏没起/端口不对;bin_present=false→ 缺 CLI)。- 询问用户本次采样时长与场景,等用户确认就位后再开采:
- 时长:10 秒(瞬时逻辑:开 UI、放技能、单次交互)/30 秒(常规玩法循环、跑图)/60 秒(长周期系统:定时器波次、偶发卡顿复现)/自定义(上限 60)。
- 场景:请用户描述准备触发什么(跑图、刷实体、开打、跑机器……),首次使用顺带确认脚本包前缀(供
name_contains)。
- 用户就位 →
tracy_native_capture(seconds=<约定时长>, name_contains="MyMod", label="before")—— 返回空看warning(多半是窗口内没负载)。 - 在对话正文完整输出热点报告(必做,格式见下节):方案按 A/B/C(或 1/2/3)编号,结尾请用户直接在聊天框回复编号(如"A+C")选定要做哪几条;禁止调用 AskUserQuestion 等选项弹窗工具收集选择。
- 按用户选择改热点函数 → 必要时用 game-testing MCP 的
reload_addon_and_game热重载 → 同样场景、同样时长再抓label="after"。 tracy_diff_captures(base_id=<before>, new_id=<after>, metric="self")—— 目标函数应在improved且delta_ms为负;总体看summary.pct,向用户回报实际省了多少毫秒。- 可选:
tracy_jank_fps(action="sample_fps")前后对比 FPS 百分位(此工具经 MCDK,MCStudio不可用)。
热点报告格式(第 4 步必做)
硬性要求:报告是对话正文,不用弹窗——下面 ①②③ 必须作为可读的正文消息完整输出(分析写在内部思考里不算输出);不要调用 AskUserQuestion 之类的选项弹窗工具,选择环节就是正文末尾一句"回复编号即可"。
① 热点排行:top 5~10 表格 —— 函数名|self_ms|calls|每帧均摊(self_ms÷frames)|单次均摊(self_ms÷calls),注明窗口 frames 与总 self_ms。均摊值比总量更能说明严重程度(例:每帧 >1ms 的单个 MOD 函数已值得警惕)。
What ships with it
7 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.
- 3d ago Changed · +3 lines 990150c980c2
- 12d ago First seen · 71 lines · 92 tokens per session scan A fcdcbbc92534
mcdk-tracy-profiling is a skill published in the GitHub repository lovelyXiaoQi/mcdk-mcp-tracy (20 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 2,456 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.