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/maplecity1314/vite-browser/vite-browser-runtime-diagnosticsnpx skills add MapleCity1314/vite-browser --skill vite-browser-runtime-diagnosticsgit clone --depth 1 https://github.com/MapleCity1314/vite-browserWrote 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/maplecity1314/vite-browser/vite-browser-runtime-diagnostics)<a href="https://agentmods.dev/skills/maplecity1314/vite-browser/vite-browser-runtime-diagnostics"><img src="https://agentmods.dev/badge/skills/maplecity1314/vite-browser/vite-browser-runtime-diagnostics.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 | $0.00152 | $0.01069 |
| Opus 5 | $0.00076 | $0.00535 |
| Sonnet 5 | $0.00030 | $0.00214 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
vite-browser-runtime-diagnostics 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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vite-browser-runtime-diagnostics
Use this skill when runtime behavior is the likely cause. Prefer it over component inspection when timing and recent updates matter.
Standard sequence
vite-browser vite runtime
vite-browser errors --mapped --inline-source
vite-browser correlate errors --mapped --window 5000
vite-browser correlate renders --window 5000
vite-browser diagnose propagation --window 5000
vite-browser diagnose hmr --limit 50
vite-browser vite hmr trace --limit 50
vite-browser vite module-graph --limit 200
vite-browser vite module-graph trace --limit 200
In v0.3.3+, errors --mapped --inline-source is also the right first read for browser-side runtime failures that never appear in the Vite overlay. Do not assume no errors means the page is healthy unless logs and the visible browser state agree.
Use diagnose propagation first when the question is about rerenders, component paths, store changes, or "what update actually flowed into this failure". Treat its output as a high-confidence propagation clue, not strict causal proof. Use diagnose hmr first when the problem still looks primarily transport/HMR-layer.
Diagnostic patterns
HMR instability
vite hmr clear- Reproduce once
vite hmr trace --limit 50- Flag
full-reloador repeatederrorevents.
Module churn
vite module-graph clear- Capture baseline:
vite module-graph - Trigger one change or one navigation
vite module-graph trace- Inspect unexpectedly added/removed modules.
Recent update caused failure
- Reproduce once after the failure.
correlate errors --mapped --window 5000- Identify whether the current error overlaps with recent HMR-updated modules.
- Inspect the highest-confidence matching module first.
Store or component propagation
- Reproduce once after the visible failure.
- Wait briefly for queued render/store events to settle if reproduction was driven by a live interaction or hot update. A short delay such as ~300ms is usually enough, though
v0.3.3+is more tolerant of sparse store-side evidence and missing browser-side HMR events in Vue/Pinia repros. correlate renders --window 5000diagnose propagation --window 5000- Use
Store Updates,Changed Keys, andRender Pathto choose the first store/component to inspect.- Vue:
vue pinia [store],vue tree - React:
react store list,react store inspect <name>,react commits --limit 20,react tree
- Vue:
- If the output is inconclusive or says no trace is available, keep the conclusion conservative and do not overstate a causal chain.
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.
- 6d ago First seen · 106 lines · 152 tokens per session scan A 37b8b8bf2b24
vite-browser-runtime-diagnostics is a skill published in the GitHub repository MapleCity1314/vite-browser (9 stars, last pushed 4mo ago), licensed MIT. It adds 152 tokens to every session and 1,069 once invoked, about $0.0008 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
d3k
Use when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. Own the runtime: reuse or background-start d3k non-interactively, wait for readiness, use its project-stable managed Chrome profile, and inspect unified browser/server evidence.
node-modules-inspector
Inspects a project's installed nodemodules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate…
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
jlink
J-Link 下载与在线调试工具,用于探测设备、烧录固件、读写内存、查看寄存器、复位目标、读取 RTT/SWO 日志, 以及在线调试(暂停/恢复/单步/断点运行/调用栈/变量查看)。 当用户提到 J-Link、JLink、RTT、烧录固件、写内存、读内存、寄存器查看、目标复位、探针连通性检查、 在线调试、单步、断点、调用栈时自动触发,也兼容 /jlink 显式调用。 即使用户只是说"烧录一下"、"看看 RTT 输出"或"调试一下",只要上下文涉及 J-Link 探针就应触发此 skill。.
openocd
OpenOCD 下载与调试工具,用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试(halt/resume/step/寄存器/内存/断点)、GDB 源码级调试,以及 Semihosting/ITM 输出捕获和底层查询。 当用户提到 OpenOCD、ST-Link、CMSIS-DAP、DAPLink、FTDI、烧录固件、擦除 Flash、GDB Server、 reset、interface/target/board 配置、openocd.cfg、在线调试、单步、断点、寄存器查看、 内存读写、semihosting 时自动触发,也兼容 /openocd 显式调用。…
serial
嵌入式串口调试工具,用于扫描串口、实时监控、发送数据、记录日志和 Hex 查看。 当用户提到串口、COM 口、UART、AT 命令调试、波特率、Hex 串流、串口抓日志、 串口监控、查看 MCU 输出、二进制协议联调时自动触发,也兼容 /serial 显式调用。 即使用户只是说"看看串口输出"、"发个 AT 命令"或"抓一下日志",只要上下文涉及 串口通信就应触发此 skill。.