dsh-env-probe
Zero-dependency DeepSeek Harness (dsh) plugin: probes the local machine environment (OS / shells / runtimes / tools / disks / proxy) once, caches the report, and injects it into every session's system prompt so the agent starts each conversation already knowing what this computer offers. Adds /env-refresh and /env-suggest slash commands where a command adapter is composed.
AI 분석
核心用途是让 AI 自动感知本地开发环境。适合需要 AI 编写和运行依赖本地特定工具链代码的开发者。支持缓存探测结果，并提供 /env-refresh 等命令。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nodata404/dsh-env-probeConfiguration
| Key | Default | Meaning |
|---|---|---|
cacheTtlHours | 168 | Cache lifetime; re-probes in background on next assembly after expiry |
order | 30 | System-prompt section order (-100 identity / 0 persona / 100-199 tool guidance) |
language | 'en' | Injected text language: 'en' / 'zh' |
cacheDir | '~/.dsh-env-probe' | Cache directory (env-profile.json + env-profile.md) |
runtimes | git, node, npm, python, python3, pip, docker, java, go, rustc | Runtimes to probe |
tools | curl, wget, ffmpeg, 7z, pandoc, tar, unzip, make, gcc, pwsh | Tools to probe |
perProbeTimeoutMs | 5000 | Per-probe timeout |
totalTimeoutMs | 30000 | Total probe budget |
concurrency | 4 | Probe concurrency |
marker | 'ENV-PROBE' | Section marker text |