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/apurvbazari/claude-plugins/wizardnpx skills add ApurvBazari/claude-plugins --skill wizardgit clone --depth 1 https://github.com/ApurvBazari/claude-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 | $0.00038 | $0.01549 |
| Opus 5 | $0.00019 | $0.00775 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
wizard 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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard Skill — Notification Preferences
You are guiding a developer through customizing their Claude Code notification preferences. This wizard configures which events trigger notifications, what sounds play, notification cooldown, and which app activates on click. Works on macOS (terminal-notifier) and Linux (notify-send).
Conversation Style
- Conversational, not interrogative — Acknowledge each answer before moving on.
- Show defaults — Always present the current default and let the developer confirm or change.
- Group questions per event — Ask 2-3 related questions together for each event, not one at a time.
- Be concise — Each exchange should be brief.
Reference Data
See references/notification-options.md for available sounds, hook events, matcher patterns, and app bundle IDs.
Wizard Flow
Step 0: Detect Platform & Editor
Detect the platform first:
uname -s
Darwin→ macOS (usesterminal-notifierwith sounds and app activation)Linux→ Linux (usesnotify-sendwith urgency levels, no custom sounds or app activation)
On macOS, detect the user's editor for the "Activate" default. Check for running processes:
ps aux | grep -i -E 'Cursor|Code|Windsurf' | grep -v grep | head -1
Map to bundle IDs:
- "Cursor" →
com.todesktop.230313mzl4w4u92 - "Code" (VS Code) →
com.microsoft.VSCode - "Windsurf" →
com.codeium.windsurf - If none detected, default to
com.microsoft.VSCodeand ask the user to confirm.
On Linux, skip the editor/bundle-ID detection and activate config — notify-send does not support click-to-focus.
Use the detected editor as the default "Activate" value for all events below (macOS only).
Walk through each of the three hook events. For each event, ask as a group:
Event 1: Task Completed (Stop hook)
Present:
Task Completed — fires when Claude finishes a response.
Notifications show a truncated version of Claude's actual response. The "message" below is a fallback — it only appears when contextual information can't be extracted.
Current defaults:
- Fallback message: "Task completed"
- Sound: Hero
- Activate:
Would you like to keep these defaults, or customize the fallback message, sound, or app?
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.
- 2d ago First seen · 183 lines · 38 tokens per session scan A a059540ad27b
wizard is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 1,549 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
change-keybinding
Customize Warp keyboard shortcuts (keybindings, keymappings) by editing the user's keybindings.yaml file. Use when the user asks to remap a key combination, rebind an action, change a shortcut, or remove a default keybinding (e.g. "change ctrl+space to ctrl+s", "rebind the command palette to cmd+p", "remove the…
agent-add-mcp
Use this skill when helping users add MCP servers to their Warp configuration.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.