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/kat3samsin/claude-code-plugins/setup-refocusnpx skills add kat3samsin/claude-code-plugins --skill setup-refocusgit clone --depth 1 https://github.com/kat3samsin/claude-code-pluginsWhat 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 | $0.00017 | $0.00566 |
| Opus 5 | $0.00009 | $0.00283 |
| Sonnet 5 | $0.00003 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade B, and why
setup-refocus scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. Configures the Stop hook in `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refocus: Never Lose Track of Your Terminal
This skill sets up clickable macOS notifications for Claude Code:
- Notification on task completion - Know when Claude is done
- Click to refocus - Activate your terminal window instantly
- Smart messages - Different notifications for different completion types
- Customizable sounds - Choose your notification sound
How to Run
Users can trigger this skill by:
- Slash command:
/refocus:setup-refocus - Ask Claude: "Set up refocus" or "I want clickable notifications when tasks complete"
What It Does
- Asks which terminal you use (iTerm2, Ghostty, or Terminal.app)
- Asks your preferred notification sound
- Creates the notification handler script at
~/.claude/hooks/refocus-handler.sh - Configures the Stop hook in
~/.claude/settings.json - Sends a test notification to confirm it works
After Setup
When Claude Code finishes a task:
- A notification appears in your macOS notification center
- Click the notification to activate your terminal window
- You're right back where you left off!
Requirements
- macOS
terminal-notifier- Install with:brew install terminal-notifierjqfor settings configuration (brew install jq)
Supported Terminals
- iTerm2 - Bundle ID:
com.googlecode.iterm2 - Ghostty - Bundle ID:
com.mitchellh.ghostty - Terminal.app - Bundle ID:
com.apple.Terminal
Customization
Changing Terminal
Re-run the setup to choose a different terminal.
Notification Sounds
Available sounds during setup:
- Hero (recommended)
- Glass
- Pop
- Submarine
- None (silent)
Manual Configuration
The hook is configured in ~/.claude/settings.json:
{
"hooks": {
"Stop": [{
"matcher": "",
"hooks": [{
"type": "command",
"command": "~/.claude/hooks/refocus-handler.sh"
}]
}]
}
}
Troubleshooting
Notification doesn't appear
- Check macOS notification settings for terminal-notifier
- Go to System Settings > Notifications > terminal-notifier
- Ensure "Allow Notifications" is enabled
What ships with it
1 file 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.
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 · 97 lines · 17 tokens per session scan B 168db292fc30
setup-refocus is a skill published in the GitHub repository kat3samsin/claude-code-plugins (2 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 566 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.