How do I install the Sysop Kernel skill?

Run npx skillmds@latest add majiayu000/sysop-kernel in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Sysop Kernel safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Sysop Kernel?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Sysop Kernel free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Sysop Kernel?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Sysop Kernel by majiayu000 — Agent Skill

Name: Sysop Kernel
Rating: 4.5 (4 reviews)
Author: majiayu000

Sysop Kernel

WSL2 system health checks and Windows-specific hardening operator kernel for SYSopGPTWSL: run a repeatable sysop pipeline (preflight, WSL healthcheck, drift check, Windows snapshot via PowerShell, perf bench), produce a diffable report, and append evidence to `learn/LEDGER.md`. Use for sysop/health checks, drift/baseline verification, or when debugging Windows/WSL interop pitfalls (UNC cwd, UTF-8 BOM in PowerShell JSON, `/mnt/c` performance) and for Windows-side hardening/performance signals (power plan, power throttling, storage/volume inventory, WSL status/version). Use Plan-first execution and explicit verification reporting.

majiayu000 Updated Sep 9, 2026 567 repo stars

File contents

SYSop Operator Kernel

Follow AGENTS.md (Plan-first; worktrees per task when parallel; verification required; auditable notes).

Plan mode (no writes yet)

Read AGENTS.md, then sysop/README_INDEX.md (index-first).
Restate the operator goal (health/drift/snapshot/bench/report).
Define “done means…”:
- fresh artifacts under sysop/out/ (at least sysop/out/report.md)
- if ./sysop/run.sh is executed: a new entry appended to learn/LEDGER.md
Hypotheses (when something fails):
- Windows interop unavailable (for example powershell.exe/vsock errors)
- UNC cwd issues (Windows commands must run from /mnt/c)
- systemctl bus blocked in the Codex runner (expected)
Minimal evidence (read-only) to gather as needed:
- ./sysop/preflight.sh
- ./sysop/healthcheck.sh
- command -v powershell.exe || command -v pwsh.exe (if Windows snapshot is requested)
Propose the exact ./sysop/run.sh ... command(s) and STOP for approval:
- ./sysop/run.sh all (writes under sysop/out/ and appends to learn/LEDGER.md)
- Optional (repo-scoped auto-fix + script generation): ./sysop/run.sh all --apply-fixes

Execution mode (after approval)

Run the approved ./sysop/run.sh ... command(s) from repo root.
Return results using the repo output format (see AGENTS.md), including:
- report path: sysop/out/report.md
- “Top bottlenecks” excerpt (if present)
- latest learn/LEDGER.md excerpt (3–8 lines)

Safety

No destructive ops (rm -rf, git reset --hard, git clean -fdx).
No writes outside the repo or to /etc.
No internet fetches.

For details and rationale, see references/OPERATOR_KERNEL.md.

---name: sysop-kerneldescription: WSL2 system health checks and Windows-specific hardening operator kernel for SYSopGPTWSL: run a repeatable sysop pipeline (preflight, WSL healthcheck, drift check, Windows snapshot via PowerShell, perf bench), produce a diffable report, and append evidence to `learn/LEDGER.md`. Use for sysop/health checks, drift/baseline verification, or when debugging Windows/WSL interop pitfalls (UNC cwd, UTF-8 BOM in PowerShell JSON, `/mnt/c` performance) and for Windows-side hardening/performance signals (power plan, power throttling, storage/volume inventory, WSL status/version). Use Plan-first execution and explicit verification reporting.--- # SYSop Operator Kernel Follow `AGENTS.md` (Plan-first; worktrees per task when parallel; verification required; auditable notes). ## Plan mode (no writes yet) 1) Read `AGENTS.md`, then `sysop/README_INDEX.md` (index-first). 2) Restate the operator goal (health/drift/snapshot/bench/report). 3) Define “done means…”: - fresh artifacts under `sysop/out/` (at least `sysop/out/report.md`) - if `./sysop/run.sh` is executed: a new entry appended to `learn/LEDGER.md` 4) Hypotheses (when something fails): - Windows interop unavailable (for example `powershell.exe`/vsock errors) - UNC cwd issues (Windows commands must run from `/mnt/c`) - `systemctl` bus blocked in the Codex runner (expected) 5) Minimal evidence (read-only) to gather as needed: - `./sysop/preflight.sh` - `./sysop/healthcheck.sh` - `command -v powershell.exe || command -v pwsh.exe` (if Windows snapshot is requested) 6) Propose the exact `./sysop/run.sh ...` command(s) and STOP for approval: - `./sysop/run.sh all` (writes under `sysop/out/` and appends to `learn/LEDGER.md`) - Optional (repo-scoped auto-fix + script generation): `./sysop/run.sh all --apply-fixes` ## Execution mode (after approval) - Run the approved `./sysop/run.sh ...` command(s) from repo root. - Return results using the repo output format (see `AGENTS.md`), including: - report path: `sysop/out/report.md` - “Top bottlenecks” excerpt (if present) - latest `learn/LEDGER.md` excerpt (3–8 lines) ## Safety - No destructive ops (`rm -rf`, `git reset --hard`, `git clean -fdx`). - No writes outside the repo or to `/etc`. - No internet fetches. For details and rationale, see `references/OPERATOR_KERNEL.md`.

Frequently asked questions