# work-completion-summary

work-completion-summary delivers audio debriefs and next steps via ElevenLabs voice synthesis after completing a task. Useful for hands-free progress updates.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 3990 repo stars
- Author: disler
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/disler/claude-code-hooks-mastery/tree/HEAD/.claude/agents/work-completion-summary.md
- Updated: 2026-03-04
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/work-completion-summary

## What it does

The agent converts task completions into a short spoken report. It drafts one sentence detailing what was done and a second sentence proposing the immediate next step, avoiding filler phrases. Then it generates an audio file via `mcp__ElevenLabs__text_to_speech`, saves it as an `.mp3` inside the local `output` directory with a timestamp, and immediately triggers playback with `mcp__ElevenLabs__play_audio`.

This subagent lacks memory of previous chat exchanges, meaning the caller must explicitly outline the completed work inside the prompt. Without an active ElevenLabs MCP server configured in your environment, audio synthesis will fail.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/work-completion-summary.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/work-completion-summary.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/work-completion-summary.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/disler/claude-code-hooks-mastery/tree/HEAD/.claude/agents/work-completion-summary.md

## When to use it
- play spoken summaries of completed coding tasks
- suggest the next logical action in one sentence
- save timestamped audio debriefs into the output folder

## Example prompts
- Give me an audio summary of the completed database migration
- Run tts summary for the changes made to the user controller

## Similar
- [speak-summary](https://affpapa.org/en/nevibecode/skills/speak-summary.md) — skill · 12 installs
- [elevenlabs-tts](https://affpapa.org/en/nevibecode/skills/elevenlabs-tts.md) — skill · 1700 installs
- [audio-jingle](https://affpapa.org/en/nevibecode/skills/audio-jingle.md) — skill · 211 installs
- [threejs-audio-generator](https://affpapa.org/en/nevibecode/skills/threejs-audio-generator.md) — skill · 3800 installs
- [elevenlabs](https://affpapa.org/en/nevibecode/skills/elevenlabs.md) — skill · 1800 installs
- [scenario-elevenlabs](https://affpapa.org/en/nevibecode/skills/scenario-elevenlabs.md) — skill · 865 installs

From the same set: [disler/claude-code-hooks-mastery](https://affpapa.org/en/nevibecode/by/disler/claude-code-hooks-mastery.md) — 25 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
