push-notification

push-notification is a skill for Claude Code from cboone/agent-harness-plugins. It costs 57 tokens per session (1,560 once invoked), scanned A, original, MIT.

A skill that sends a notification to a user's phone through ntfy, a service for delivering push messages. It can be called directly or by another skill when work finishes or needs a decision.

In plain words
What is it for?
Use it to send a custom or automatically composed phone alert, with optional title, priority, tags, link, or dry-run mode.
Why use it?
It lets users know about completed work or required input even when the coding session is running remotely or in the cloud.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the push-notification plugin — 1 skill shipped together

Good fit Use it to send a custom or automatically composed phone alert, with optional title, priority, tags, link, or dry-run mode.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add cboone/agent-harness-plugins
Claude Code
/plugin install push-notification

Made for: Claude Code.

Or install push-notification, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for push-notification

README.md
[![agentmods](https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/push-notification/github.svg)](https://agentmods.dev/skills/cboone/agent-harness-plugins/push-notification)
Your own site
<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/push-notification"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/push-notification/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for push-notification

Your own site · 80×15
<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/push-notification"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/push-notification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01560
Opus 5.5 $0.00023 $0.00624
Sonnet 5.5 $0.00011 $0.00312
Haiku 4.5 $0.00006 $0.00156

Measured 5d ago against content hash 9c7c0d6164ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

push-notification 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 5d 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.

plugins/push-notification/skills/push-notification/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Push Notification

Send one push notification through the user's configured backend, so it reaches their phone wherever this session runs, including remote and cloud sessions. A bundled helper sends it, keeps the token and topic out of the transcript and the process list, and reports what is missing when nothing is configured.

For a local Mac banner when a session stops or asks for input, use the notify hook plugin. This skill sends messages an agent or a skill decides to send.

Options

The user may provide these inline:

  • [message]: What to say. When absent, compose it from the work just done, following Writing the notification
  • --title <text>: Use this title instead of a composed one
  • --priority <level>: min, low, default, high or urgent
  • --tag <tag>: Add a tag or emoji shortcode such as white_check_mark; repeatable
  • --click <url>: Open this URL when the notification is tapped
  • --dry-run: Show the request that would be sent, without the topic or token, and send nothing

A request to be notified later ("notify me when CI passes") is a request to send at that point: do the work or the wait first, then send once with the outcome. Never send a placeholder now and the real result later.

The Helper

bash "${CLAUDE_PLUGIN_ROOT}/scripts/push-notification" check
bash "${CLAUDE_PLUGIN_ROOT}/scripts/push-notification" send --title TITLE --message BODY [--priority LEVEL] [--tag TAG]... [--click URL] [--dry-run]

Claude Code replaces the plugin-root placeholder with the installed plugin's directory before this file reaches you. Where the placeholder arrives unsubstituted, as in Codex CLI, the script is ../../scripts/push-notification relative to the directory that holds this SKILL.md; resolve that path once and use it in every command.

For a body with quotes, newlines or shell metacharacters, pass --message - and send the body on stdin through a quoted heredoc, so the shell does not expand it.

Read the full file on GitHub · 89 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 89 lines · 57 tokens per session scan A 9c7c0d6164ed

Subscribe to this mod's changes

push-notification is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,560 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-12.