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/skycaier/sky-windows-remote-executor/remote-executor-systemnpx skills add skycaier/sky-windows-remote-executor --skill remote-executor-systemgit clone --depth 1 https://github.com/skycaier/sky-windows-remote-executorWhat 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 | $0.00032 | $0.00880 |
| Opus 5 | $0.00016 | $0.00440 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
remote-executor-system 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 yesterday.
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.
curl -s -X POST http://<host>:8765/process/list \ How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Executor 系统层 (v3.5)
注意: 此 skill 由关键词触发加载,不要常驻。
端点
进程管理
列出进程
POST /process/list
Content-Type: application/json
{
"filter": "python", // 可选,按名称过滤
"sort_by": "memory", // memory, cpu, name
"limit": 30
}
返回:
{
"processes": [
{"pid": 1234, "name": "python.exe", "cpu": 5.2, "memory_mb": 256}
],
"count": 1
}
结束进程
POST /process/kill
Content-Type: application/json
{"pid": 1234} // 按 PID
// 或
{"name": "python"} // 按名称模糊匹配
注册表
读取注册表
POST /reg/read
Content-Type: application/json
{
"key": "HKLM\\Software\\Microsoft\\Windows\\CurrentVersion",
"value_name": "ProgramFilesDir"
}
写入注册表
POST /reg/write
Content-Type: application/json
{
"key": "HKCU\\Software\\MyApp",
"value_name": "Setting",
"data": "123",
"reg_type": "REG_SZ" // REG_SZ, REG_DWORD, REG_QWORD, REG_BINARY, REG_MULTI_SZ
}
Windows 服务
列出服务
POST /service/list
Content-Type: application/json
{"filter": ""} // 可选过滤
启动服务
POST /service/start-svc
Content-Type: application/json
{"name": "ServiceName"}
停止服务
POST /service/stop-svc
Content-Type: application/json
{"name": "ServiceName"}
计划任务
列出计划任务
POST /task/list
Content-Type: application/json
{"filter": ""}
创建计划任务
POST /task/create
Content-Type: application/json
{
"name": "MyTask",
"command": "python D:\\script.py",
"schedule": "DAILY" // ONCE, DAILY, WEEKLY, MONTHLY
}
删除计划任务
POST /task/delete
Content-Type: application/json
{"name": "MyTask"}
使用示例
查看 Python 进程:
curl -s -X POST http://<host>:8765/process/list \
-H "Content-Type: application/json" \
-d '{"filter": "python", "sort_by": "memory", "limit": 10}'
结束进程:
curl -s -X POST http://<host>:8765/process/kill \
-H "Content-Type: application/json" \
-d '{"pid": 1234}'
读取注册表:
curl -s -X POST http://<host>:8765/reg/read \
-H "Content-Type: application/json" \
-d '{"key": "HKLM\\Software\\Microsoft\\Windows\\CurrentVersion", "value_name": "ProgramFilesDir"}'
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.
- yesterday First seen · 156 lines · 32 tokens per session scan A 1577dd81810e
remote-executor-system is a skill published in the GitHub repository skycaier/sky-windows-remote-executor (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 880 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.