agentleFS
Sign inStart free
rlajousrlajous/claude-code-commands/skills/notifications/SKILL.md

notifications

Skill30 starsChanged 3 months agoMITView on GitHub

Configure and diagnose opt-in desktop notifications for completed Claude Code or Codex turns and new reviews on pull requests you authored. Use when the user asks to enable agent-finished alerts, watch approvals or requested changes on their PRs, inspect notification configuration, or get the background daemon command.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No argument → show the resolved configuration with python3 "{SKILL_DIR}/scripts/notification_config.py", explain which channels are …

    line 21
  2. Very specific:

    Read .git-workflow/config.yaml, then the legacy .claude/config.yaml fallback:

    line 30

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Git Workflow Notifications

Resolve {SKILL_DIR} to the absolute, physical directory containing this loaded SKILL.md. If the host cannot expose the path, use PLUGIN_ROOT, then CLAUDE_PLUGIN_ROOT, only to locate skills/notifications/SKILL.md. Verify every requested resource exists. Never substitute an empty variable or silently fall back to /scripts.

Commands

  • --doctor → run bash "{SKILL_DIR}/scripts/notification-tools.sh" --doctor, report the output, and exit. The check must not query pull requests, create state, or emit a desktop notification.
  • --daemon-command → run bash "{SKILL_DIR}/scripts/notification-tools.sh" --daemon-command, print the absolute command unchanged, and exit.
  • No argument → show the resolved configuration with python3 "{SKILL_DIR}/scripts/notification_config.py", explain which channels are enabled, and print the daemon command when PR activity or review requests are enabled.

The daemon is required for GitHub activity. Agent-complete notifications use the plugin's Stop hook and do not require the daemon.

Configuration

Read .git-workflow/config.yaml, then the legacy .claude/config.yaml fallback:

notifications:
  agentComplete: false
  prActivity: false
  sound: Glass

Both channels are opt-in. notifications.sound applies to all Git Workflow notifications. When it is absent, accept reviewWatch.sound as a compatibility fallback, then use Glass.

Expected events

Agent completion announces only the main turn. Do not add SubagentStop or failure alerts. GitHub activity announces submitted APPROVED, CHANGES_REQUESTED, and COMMENTED reviews on open PRs authored by the authenticated user. General PR comments, CI, merges, dismissals, and commits are outside this workflow.

Notification failures are best effort and must never fail a turn or review workflow. Do not read or persist full transcripts; the completion adapter uses only the first useful line of last_assistant_message and stores only a deduplication digest.

Runtime compatibility

Claude invokes this skill as /notifications; Codex invokes it as $notifications. Keep shared behavior host-neutral. Claude loads hooks/claude-hooks.json, Codex plugins load hooks/hooks.json, and a source checkout exposes the project hook through .codex/hooks.json.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free