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/setupnpx skills add ApurvBazari/claude-plugins --skill setupgit 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 | $0.00044 | $0.02898 |
| Opus 5 | $0.00022 | $0.01449 |
| Sonnet 5 | $0.00009 | $0.00580 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade A, and why
setup 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 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.
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Skill — Notification Setup
You are running the notify setup skill. This installs and configures system notifications for Claude Code. Supports macOS (terminal-notifier) and Linux (notify-send).
Overview
Tell the developer:
Starting notify setup — I'll check dependencies, walk you through notification preferences, and configure hooks so you get native system notifications when Claude completes tasks or needs your attention.
Dry-Run Mode
If the user includes "dry-run" or "--dry-run" in their command arguments:
- Run all steps normally (dependency check, scope selection, customization)
- At Step 6 (Generate Artifacts), instead of writing files, display what would be written:
- Show the
notify.shscript content - Show the hook entries that would be merged into
settings.json - Show the
notify-config.jsoncontent
- Show the
- Skip Step 7 (Test) and Step 8 (Handoff)
- End with: "Dry run complete — no files were written. Re-run without
--dry-runto apply."
Step 1: Detect Platform & Check Dependencies
Run uname -s to detect the platform.
macOS (Darwin):
Run command -v terminal-notifier via Bash.
- If installed:
terminal-notifier is installed. Good to go. - If missing: offer to install via
${CLAUDE_PLUGIN_ROOT}/scripts/install-notifier.sh. If Homebrew is also missing, show install instructions and stop.
Linux:
Run command -v notify-send via Bash.
- If installed:
notify-send is available. Good to go. - If missing: show installation instructions from
${CLAUDE_PLUGIN_ROOT}/scripts/install-notifier.shoutput (distro-specificapt/dnf/pacmancommands) and stop.
Note: On Linux, sounds are not supported (mapped to urgency levels) and click-to-focus (activate) is not available. Inform the developer of these differences.
Step 2: Choose Install Scope
Ask the developer to choose an install scope:
Where should notifications be configured?
- Global (default) — Notifications for all projects (
~/.claude/)- This project only — Notifications scoped to this project directory (
$PWD/.claude/)
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 · 303 lines · 44 tokens per session scan A acd44775c6e4
setup is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 44 tokens to every session and 2,898 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
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
subagent
Spawn and manage autonomous background agents for parallel work.
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem. Use when spawning subagents that need codebase context they cannot predict upfront, or when building multi-agent workflows where context is progressively refined.
audit-installation
Аудит пользовательской инсталляции IWE. Запускает scripts/iwe-audit.sh + MCP healthcheck + smoke-test ритуала через sentinel-механику (контракт dry-run-contract.md), передаёт отчёт subagent'у в роли VR.R.002 Аудитор (context isolation) → verdict ✅/⚠️/❌ по 6 компонентам (Inventory, L1 drift, DS-strategy, L3…