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 GoogilyBoogily/googilyboogily-claude-power-tools --skill debug-linux-desktopgit clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-toolsWrote 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/googilyboogily/googilyboogily-claude-power-tools/debug-linux-desktop)<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/debug-linux-desktop"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/debug-linux-desktop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/debug-linux-desktop"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/debug-linux-desktop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00202 | $0.02900 |
| Opus 5.5 | $0.00081 | $0.01160 |
| Sonnet 5.5 | $0.00040 | $0.00580 |
| Haiku 4.5 | $0.00020 | $0.00290 |
Grade D, and why
debug-linux-desktop scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **`sudo dd` / `mkfs`** as a "fix" for anything other than the literal "I want to wipe this device" case. Confirm with the user before any block-device write. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **`rm -rf ~/.config`** to "reset" a desktop. It nukes user state. Move to a backup directory instead. How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Linux Desktop
Symptom-first diagnostic playbook for Linux desktop systems. The user is in pain — be systematic, prove each hypothesis with a command, and don't guess.
Operating Principles
-
Prove before fixing. Every hypothesis needs a confirming diagnostic command before you suggest a fix. Linux desktop issues are heavily multi-causal — a black screen could be GPU driver, display server, display manager, kernel module, or kmsfb fighting fbcon. Running
dmesg | tail -50andjournalctl -b -p erris almost always step one. -
Identify the environment first. Fixes are distro-, init-, session-, and driver-specific. Before recommending anything, capture the baseline:
. /etc/os-release && echo "$PRETTY_NAME" && uname -r echo "Session: ${XDG_SESSION_TYPE:-unset} / Desktop: ${XDG_CURRENT_DESKTOP:-unset}" loginctl show-session "$(loginctl | awk '/seat/{print $1; exit}')" -p Type -p Remote 2>/dev/null lspci -k | grep -EA3 'VGA|3D|Display' -
Don't reset the system without explicit user approval. Reinstalling drivers, regenerating initramfs, or rebooting are user-confirmed actions. The user's CLAUDE.md is explicit on this.
-
Read logs before reading forums.
dmesg,journalctl,~/.local/share/xorg/Xorg.0.log,~/.cache/gdm/session.logare authoritative. Forum posts may be outdated or distro-mismatched. If you do search the web (via WebSearch/WebFetch), prefer Arch wiki, Fedora docs, freedesktop.org, kernel.org bug tracker, and Phoronix over random Stack Overflow answers. -
Use sequential thinking on complex multi-symptom issues. Multi-monitor + Nvidia + Wayland + suspend bug is a 4-axis problem. Externalize the reasoning.
Step 0: Capture Context
Before suggesting anything, ask the user (or detect from terminal access) the answers to these. Don't loop more than once — make reasonable assumptions if the user is short on time.
| What | How |
|---|---|
| Distro + version | cat /etc/os-release |
| Kernel | uname -r |
| GPU | lspci -k | grep -EA3 'VGA|3D|Display' |
| Driver in use | check Kernel driver in use: line of above |
| Session type | echo $XDG_SESSION_TYPE (wayland or x11) |
| Desktop | echo $XDG_CURRENT_DESKTOP (GNOME, KDE, Hyprland, sway, etc.) |
| Display manager | systemctl status display-manager |
| Recent change | "What changed? kernel update? driver install? config edit?" |
| Reproducer | "Does it happen every boot? Only on resume? Only with X app?" |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/audio-pipewire.md 7.1 KB
- references/boot-systemd.md 8.6 KB
- references/filesystem.md 7.0 KB
- references/kernel-modules.md 7.5 KB
- references/mesa.md 8.2 KB
- references/network.md 7.4 KB
- references/nvidia.md 10 KB
- references/package-manager.md 7.1 KB
- references/sandbox-flatpak.md 7.6 KB
- references/suspend.md 6.9 KB
- references/wayland.md 8.8 KB
- references/x11.md 5.6 KB
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.
- 1mo ago First seen · 171 lines · 202 tokens per session scan D a3e931e7fb72
debug-linux-desktop is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 5mo ago), licensed MIT. It adds 202 tokens to every session and 2,900 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when the device is managed by Catalyst Center and you want its…