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/uninstallnpx skills add ApurvBazari/claude-plugins --skill uninstallgit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/uninstall)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/uninstall"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/uninstall.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00853 |
| Opus 5 | $0.00017 | $0.00426 |
| Sonnet 5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
uninstall 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uninstall Skill — Remove Notification Setup
You are running the notify uninstall skill. This cleanly removes all notification hooks, scripts, and config files installed by the notify plugin.
Step 1: Detect Install Scope
Check both locations for notify artifacts:
- Global:
~/.claude/hooks/notify.sh,~/.claude/notify-config.json - Project:
$PWD/.claude/hooks/notify.sh,$PWD/.claude/notify-config.json
If found in both:
I found notify installed in two locations:
- Global (
~/.claude/)- This project (
$PWD/.claude/)Which would you like to uninstall?
- Global only
- This project only
- Both
If found in one location, proceed with that location. Set BASE_DIR accordingly.
If not found in either:
No notify installation found. Nothing to uninstall.
Stop.
Step 2: Confirm
This will remove:
$BASE_DIR/hooks/notify.sh— the notification script$BASE_DIR/notify-config.json— your notification preferences- Hook entries in
$BASE_DIR/settings.jsonthat referencenotify.shYour other hooks and settings will not be affected.
Proceed with uninstall?
Wait for confirmation. If declined, stop.
Step 3: Remove Hook Entries from settings.json
Read $BASE_DIR/settings.json. Remove only hook entries whose command field contains notify.sh. Preserve all other hooks and settings.
For each hook event (Stop, Notification, SubagentStop):
- If the hooks array for that event contains a notify hook, remove that specific entry
- If the hooks array becomes empty after removal, remove the empty array key
- If the
hooksobject becomes empty, remove it
Write the updated settings.json back.
Step 4: Delete Notify Files
rm -f "$BASE_DIR/hooks/notify.sh"
rm -f "$BASE_DIR/notify-config.json"
If $BASE_DIR/hooks/ directory is now empty, remove it:
rmdir "$BASE_DIR/hooks" 2>/dev/null || true
Step 5: Verify
Read $BASE_DIR/settings.json and confirm no notify hooks remain.
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.
- 4d ago First seen · 98 lines · 34 tokens per session scan A dd8184e8b50a
uninstall is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 853 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.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…