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 1072636071/win-shell-mcp --skill jx-testgit clone --depth 1 https://github.com/1072636071/win-shell-mcpWrote 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/1072636071/win-shell-mcp/jx-test)<a href="https://agentmods.dev/skills/1072636071/win-shell-mcp/jx-test"><img src="https://agentmods.dev/badge/skills/1072636071/win-shell-mcp/jx-test.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 | $0.00094 | $0.03065 |
| Opus 5 | $0.00047 | $0.01533 |
| Sonnet 5 | $0.00019 | $0.00613 |
| Haiku 4.5 | $0.00009 | $0.00307 |
Grade A, and why
jx-test scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP | curl / fetch | `net_get` / `net_post`；下载落盘用 `net_download` | This is a copy
89% identical to jx-mode — 60 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JX Test 模式细则
JX Test 模式 = JX 模式（标准能力 + 规则一、二）+ 规则三（bug 登记）。规则要点已写在 persona 里，本文件是执行细则。
规则一：工具优先 win-shell-mcp
win-shell-mcp 0.2.0 起全量 58 个工具，下表按操作类型全覆盖。
| 要做的事 | 绕开 | 优先调用 |
|---|---|---|
| 读文件 | 内置 read / cat / Get-Content |
fs_read（带行号）；要原始全文用 cat |
| 写/覆盖文件 | 内置 write / 重定向 | fs_write（默认 utf-8，支持 gbk 与追加） |
| 定点修改 | 内置 edit | text_replace（pattern 默认字面量、/正则/ 启用正则；字面量模式 $1 原样插入，正则模式才 $1 回引用；多命中须表态——all:true 全量 / maxReplace:N 限量 / 正则尾 g；0 命中报 EINVAL） |
| 找文件路径 | 内置 glob / find |
search_glob；按名字递归找用 find；找 PATH 里可执行文件用 search_which |
| 搜内容 | 内置 grep / grep |
search_content（跨文件）；单文件带上下文用 text_grep；两者的 pattern 与 text_replace 同一套双模语义 |
| 列目录 | ls / 内置列目录 |
fs_list（glob 过滤、recursive、sort） |
| 文本切片与统计 | head / tail / wc | text_head / text_tail / text_wc |
| 文本对比 | diff | text_diff（行级 unified diff） |
| 复制/移动/删除/建目录 | cp mv rm mkdir |
fs_cp / fs_mv / fs_rm / fs_mkdir |
| 元数据 | stat touch du |
fs_stat / fs_touch / fs_du |
| 当前目录与回显 | pwd / echo | pwd / echo |
| 执行外部程序 | 直调 pwsh/bash/cmd | run_command（argv 直执行，不经 shell 解析）；确需 shell 语法时 shell_exec |
| 环境变量 | $env: / export |
env_get / env_set / env_unset |
| 进程 | tasklist / kill | process_list / process_kill |
| 包管理 | 直调 npm/pip | pkg_detect 探测 → pkg_run 执行 |
| git | 手敲 git 命令 | git_status git_add git_commit git_diff git_log git_branch git_checkout git_clone git_pull git_push git_stash（stash 的 push/pop/list/drop 都走它的 action 参数） |
| HTTP | curl / fetch | net_get / net_post；下载落盘用 net_download |
| 网络诊断 | ping/nslookup/netstat | ping / net_dns / net_tcp / net_listen |
| 归档 | tar / zip | archive_create / archive_extract |
| 校验和 | sha256sum | hash_file |
| JSON 取值 | jq | json_get |
| 系统信息 | uname / df / free | system_info / system_disk / system_memory / system_path |
回退规则
win-shell-mcp 是首选，不是枷锁。以下情况允许回退到内置工具：
- MCP 未连接或工具不存在：直接用内置工具，无需解释。
- 调用失败且换内置确实能成：回退一次即可，并在回复中注明「
<工具名>失败（错误码），已回退」。禁止反复重试同一失败调用。 - 交互式/TUI 场景（需要人实时输入的程序）：win-shell-mcp 覆盖不了，改用内置方案并告知局限。
- 需要沙箱审批语义的场景：DSH 内置 pwsh/write/edit 自带沙箱与审批策略；涉及越权重试时以内置通道为准。
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 · 155 lines · 94 tokens per session scan A 350cc6b89d29
jx-test is a skill published in the GitHub repository 1072636071/win-shell-mcp (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,065 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to jx-mode, differing in 60 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.