agentmods.dev

bark-notify-setup

bark-notify-setup is a skill for Claude Code from RUIIIOVO/claude-code-bark-notify. It costs 58 tokens per session (962 once invoked), scanned B, original, MIT.

A setup skill that configures Bark completion notifications for Claude Code on macOS, Linux, or Windows. Bark is an iPhone app that receives push notifications through a personal URL.

In plain words
What is it for?
Detect the operating system, check the Bark push URL and encryption choice, create the sender script, and merge notifications for completed, failed, ended, or other Claude Code events.
Why use it?
It removes the manual work of creating the local notification script and adding the required Claude Code hooks to the settings file.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the bark-notify plugin — 4 skills shipped together

not rated 4repo changed 1mo ago B scan 58 tokens original MIT

Good fit Detect the operating system, check the Bark push URL and encryption choice, create the sender script, and merge notifications for completed, failed, ended, or other Claude Code events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup
View source ↗ RUIIIOVO/claude-code-bark-notify
Install

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.

Any agent
npx skills add RUIIIOVO/claude-code-bark-notify --skill bark-notify-setup
Clone the repo
git clone --depth 1 https://github.com/RUIIIOVO/claude-code-bark-notify

Made for: Claude Code.

Or install bark-notify, the plugin that ships this one along with the rest of its 4 skills.

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 bark-notify-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup/github.svg)](https://agentmods.dev/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup)
Your own site
<a href="https://agentmods.dev/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup"><img src="https://agentmods.dev/badge/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup/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 bark-notify-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup"><img src="https://agentmods.dev/badge/skills/ruiiiovo/claude-code-bark-notify/bark-notify-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00058 $0.00962
Opus 5.5 $0.00023 $0.00385
Sonnet 5.5 $0.00012 $0.00192
Haiku 4.5 $0.00006 $0.00096

Measured 1mo ago against content hash 97a396c9df19, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

bark-notify-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 1mo 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.

description: Set up Bark completion notifications for Claude Code on macOS by safely writing the local Bark sender script and merging a Stop hook into ~/.claude/settings.json. Use when the user explicitly asks to configu
skills/bark-notify-setup/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bark Notify Setup

Configure the current macOS Claude Code environment to send a Bark notification when Claude finishes a turn.

Goals

After setup, the local machine should contain:

  • ~/.claude/claude-stop-bark.sh
  • hooks in ~/.claude/settings.json for Stop, StopFailure, SessionEnd, and Notification that all run that script asynchronously

Required behavior

  1. Confirm Bark prerequisites first.

    • Read ../bark-notify/references/bark-prereqs.md.
    • Make sure the user has a Bark push URL.
    • Ask whether they want plain mode or encrypted mode.
    • If encrypted mode, require a 16-character key and remind them to match Bark app settings on iPhone.

  2. Inspect current Claude config before writing.

    • Read ~/.claude/settings.json if it exists.
    • Never overwrite unrelated settings.
    • Merge in the Stop, StopFailure, SessionEnd, and Notification hooks safely.

  3. Use the config templates from ../bark-notify/references/config-patterns.md.

    • Write a small shell script to ~/.claude/claude-stop-bark.sh.
    • Parse hook_event_name, reason, and cwd from the stdin JSON payload using python3 -c "..." (do NOT use a python heredoc — it collides with the piped stdin payload). Do NOT read $HOOK_EVENT — Claude Code does not set that env var.
    • Branch the notification per the event-types table in config-patterns.md:
      • Stop → ✅ Claude Code 已完成, level active
      • Notification → 🔔 Claude Code 等待操作, level timeSensitive. Filter: parse notification_type from the payload; only send for permission_prompt and elicitation_dialog. For idle_prompt, auth_success, elicitation_complete, elicitation_response → exit 0 silently. If notification_type is missing (older payload schema), fall back to checking message: skip when it contains "waiting for your input" or "idle", otherwise send.
      • StopFailure → ❌ Claude Code 出错, level timeSensitive
      • SessionEnd with reason ∈ {clear, logout, prompt_input_exit} → exit 0 immediately, no notification, no bell (this is the user closing the CLI)
      • SessionEnd with any other reason → ⚠️ Claude Code 会话异常结束, level timeSensitive
    • Do NOT set the sound field (audio cues opted out). Body emoji + level already differentiate events.
    • title = project name (basename of cwd); do NOT set the icon field (Cloudflare gates the official Claude icon; let Bark use its default).
    • End the script with printf '\a' (terminal bell) for tmux/terminal notifications. The user-initiated SessionEnd branch must exit before reaching the bell too.

Read the full file on GitHub · 60 lines

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. 1mo ago Changed · -30 lines 97a396c9df19
  2. 1mo ago First seen · 90 lines · 58 tokens per session scan B ebe8551e5f96

Subscribe to this mod's changes

bark-notify-setup is a skill published in the GitHub repository RUIIIOVO/claude-code-bark-notify (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 962 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude CodeProductivitybarkdeveloper-toolshooksiosnotifications
Related

Other skills, from other repositories

repo-context

Load a compact snapshot of the current repository into context — structure, stack, docs, git state.

DefaultPerson/agent-setup · 23 tokens

publish

Publish the current repository to GitHub, or review and update its GitHub setup.

DefaultPerson/agent-setup · 19 tokens

commit

A tool for creating Git commits in the Conventional Commits format, a shared way to describe changes consistently. It checks the current branch and changes before committing.

DefaultPerson/agent-setup · 61 tokens

push-and-pr

A Git workflow for pushing the current branch and opening a GitHub pull request, which is a request to review and merge code. It follows a rebase-based workflow and prepares a structured pull request.

DefaultPerson/agent-setup · 56 tokens

novu-design-workflow

Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state. Applies to BOTH dashboard-authored and code-first (@novu/framework) workflows. Use when planning a new workflow, deciding which channels to include…

novuhq/novu · 114 tokens

novu-manage-preferences

Configure notification preferences in Novu at the workflow and subscriber level. Set default channel preferences (email, SMS, push, chat, in-app), mark preferences as read-only or subscriber-editable, and manage subscriber-specific overrides. Use when setting up notification opt-in/opt-out, configuring per-channel…

novuhq/novu · 76 tokens