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 Smirnov-Labs/claude-skills --skill quickshell-bargit clone --depth 1 https://github.com/Smirnov-Labs/claude-skillsWrote 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/smirnov-labs/claude-skills/quickshell-bar)<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/quickshell-bar"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/quickshell-bar/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/smirnov-labs/claude-skills/quickshell-bar"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/quickshell-bar.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 | $0.00250 | $0.03418 |
| Opus 5.5 | $0.00100 | $0.01367 |
| Sonnet 5.5 | $0.00050 | $0.00684 |
| Haiku 4.5 | $0.00025 | $0.00342 |
Grade A, and why
quickshell-bar scanned grade A with 0 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on the hexane Quickshell bar
Overview
The default hexane bar is Quickshell 0.3.0 (Qt6/QML), running as qs (replaced waybar because waybar's workspace click-to-switch broke on Hyprland 0.56's Lua dispatch — see the hyprland-lua skill). Config lives in ~/.dotfiles/quickshell/, a directory symlink to ~/.config/quickshell/. Layout is FLAT — Quickshell auto-imports uppercase-neighbor .qml files, so there is no qmldir and no per-file imports of siblings. Entry point: shell.qml.
Core principle: hot-reload is unreliable through Edit-tool writes + the dir symlink, so never trust "I edited it, it's live" — RELAUNCH qs and QA visually with a screenshot. Most "it didn't work" moments are a stale process or a locked screen, not your code.
Source of truth for facts/gotchas: ~/docs/docs/systems/hexane/hyprland-bars.md (KB) and the design spec ~/.dotfiles/docs/superpowers/specs/2026-08-05-quickshell-bar-design.md. This skill is the how-to-work-on-it companion.
When this applies
- The bar renders all-black or blank after an edit (or in a screenshot).
- A module you added doesn't show, or
qswon't start / logs a QML error. - A PopupWindow (e.g. a slider) lands at bar-level or off to the side.
- A workspace shows a neutral dot instead of the window's app icon.
- A blocklet script works when you run it but the bar shows stale/empty/
?. - You need to add/restyle a module, or run the edit → relaunch → screenshot loop.
The dev loop (do this every time)
- Edit
~/.dotfiles/quickshell/*.qml(orlib/*). The symlink means changes are on disk immediately. - Relaunch (never rely on hot-reload):
⚠️ Launch viapkill -x qs; hyprctl dispatch 'hl.dsp.exec_cmd("qs >/tmp/qs.log 2>&1")'hyprctl dispatch exec— the agent shell sandbox kills direct GUI spawns (exit 144). (hl.dsp.exec_cmdis the Lua dispatch; see thehyprland-luaskill.) - Check the log:
grep -iE 'error|warning|invalid|not a type' /tmp/qs.log."Configuration Loaded"= clean parse; QML errors printfile:line. (Ansni.watcherStatusNotifierItem warning is benign.) - Screenshot to QA (see below). Iterate.
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.
- 5d ago First seen · 113 lines · 250 tokens per session scan A 22962e6cb870
quickshell-bar is a skill published in the GitHub repository Smirnov-Labs/claude-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 250 tokens to every session and 3,418 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…