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/dz1922/claude-notify/setupnpx skills add dz1922/claude-notify --skill setupgit clone --depth 1 https://github.com/dz1922/claude-notifyWrote 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/dz1922/claude-notify/setup)<a href="https://agentmods.dev/skills/dz1922/claude-notify/setup"><img src="https://agentmods.dev/badge/skills/dz1922/claude-notify/setup.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 | $0.00019 | $0.00980 |
| Opus 5 | $0.00010 | $0.00490 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade B, and why
setup 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Add the channel to existing `NOTIFY_CHANNELS` (don't replace) and set credentials in `~/.claude/settings.json` under `env`: How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notification Center Setup
Default Behavior
Desktop notifications are enabled out of the box. No configuration needed.
Commands
/notify:setup # Show status, offer to add channels
/notify:setup telegram # Add Telegram
/notify:setup slack # Add Slack
/notify:setup teams # Add Teams
/notify:setup lark # Add Lark/Feishu
/notify:setup webhook # Add custom webhook
/notify:setup off telegram # Remove Telegram (deletes credentials)
/notify:setup off all # Remove all channels (needs confirmation)
Flow: No argument
Show current status, then gently offer options:
Desktop notifications are active (default).
You can also receive notifications on other channels:
- telegram — Telegram bot messages
- slack — Slack incoming webhook
- teams — Microsoft Teams webhook
- lark — Lark/Feishu custom bot
- webhook — Custom HTTP endpoint
Want to add any?
Do NOT force the user to pick. Desktop is already working.
Flow: Add channel
Guide the user through configuring that specific channel:
telegram:
- Ask for bot token (from @BotFather)
- Ask for chat ID (from @userinfobot)
slack:
- Ask for incoming webhook URL
teams:
- Ask for incoming webhook URL (supports both legacy and Power Automate workflows)
lark:
- Ask for custom bot webhook URL
webhook:
- Ask for webhook URL
Write configuration
Add the channel to existing NOTIFY_CHANNELS (don't replace) and set credentials in ~/.claude/settings.json under env:
{
"env": {
"NOTIFY_CHANNELS": "desktop,telegram",
"NOTIFY_TELEGRAM_TOKEN": "bot-token-here",
"NOTIFY_TELEGRAM_CHAT": "chat-id-here"
}
}
IMPORTANT: Read the existing settings.json first and MERGE — never replace existing env vars.
Test the notification
After configuring a new channel, test it:
echo '{"cwd":"'$PWD'"}' | CLAUDE_HOOK_EVENT=TaskCompleted NOTIFY_CHANNELS=<new-channel> <credentials> ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh
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.
- 3d ago First seen · 119 lines · 19 tokens per session scan B 53e2e67e2382
setup is a skill published in the GitHub repository dz1922/claude-notify (1 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 980 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
slack-cli
Complete Slack Web API CLI — 201 methods across 29 command groups. Every public endpoint. Agent-friendly JSON output. Auto-generated from the official OpenAPI spec + @slack/web-api SDK. Use when: sending messages, reading channels, adding reactions, managing files, searching, pins, bookmarks, reminders, user groups…
slack-messages
Send Slack messages to channels or users via the elnora-slack CLI. Resolves channel/user IDs from the cached workspace reference, formats messages, handles threads and DMs, and enforces a draft-and-approve gate before anything is sent. TRIGGERS: "send slack", "slack message", "post on slack", "message on slack", "tell…
tailwind-design-system
Build production-ready design systems with Tailwind CSS v4, including CSS-first configuration, design tokens, component variants, and accessibility. Use when working with Tailwind projects.
mobile-android-design
Build modern Android apps with Material Design 3 and Jetpack Compose, including theming, navigation, adaptive layouts, and accessibility. Use for Android UI tasks.
swiftui-expert-skill
Build, review, or improve SwiftUI features with correct state management, modern API usage, Swift concurrency, and iOS 26+ Liquid Glass styling. Use for any SwiftUI task.
configure
Configure the claude-lark-plugin by managing /.claude/channels/lark/.env. Use when the user asks to configure, setup, or change Lark/Feishu settings or credentials.