mcpField
A
agent-wrapped

agent-wrapped

github.com/vkpdeveloperCreative & media06 installsUpdated 4d ago
Repository

About agent-wrapped

Agent Wrapped turns local agent history into a video recap for reviewing sessions, recurring corrections, and a usage persona. Analysis and rendering happen locally, and the data is not uploaded.

Key features

  1. 01Count sessions across supported agents
  2. 02Group recurring agent corrections
  3. 03Edit the recap data
  4. 04Render a recap video locally
  5. 05Choose vertical or square format

Use cases

  1. 01Review agent use over a period
  2. 02Turn repeated corrections into rules
  3. 03Create a video recap to review before sharing

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/vkpdeveloper/agent-wrapped --skill agent-wrapped

After installing, type/agent-wrappedin Claude Code to confirm it loaded.

Bundled fileswrapped.sh

Details

From the project README

Agent Wrapped

Run everything through wrapped.sh next to this file. On first use it downloads the latest agent-wrapped release for this OS and CPU from GitHub into ~/.local/share/agent-wrapped (a 40 to 60 MB download), and it checks for a newer release at most once a day, so never install anything by hand. The first video on a machine also downloads Chrome Headless Shell, so allow a few minutes for it.

Everything is read and rendered locally. Nothing is uploaded.

1. Read the history

<skill-dir>/wrapped.sh stats -o "${TMPDIR:-/tmp}/wrapped.json"

It finds every supported agent with local history, ranks them by session count, and prints a one-line summary. Add --year 2025 for another year and --name "..." if the user gives a name for the first card. The JSON holds prompt excerpts, so keep it in the temp directory, never in a project.

2. Write the lessons

Read corrections.samples in the JSON: real prompts where the user pushed back on their agent. Group them by what the agent kept getting wrong and write up to 3 lessons, most frequent first:

  • rule: an instruction the user could paste into CLAUDE.md or AGENTS.md, at most 8 words, imperative and concrete ("Use bun, never npm", "Run the tests before saying done", "Ask before deleting files").
  • count: how many of the samples that rule covers. Count honestly; the video prints it.

Skip one-off complaints and anything that names a person, client or secret. Leave lessons empty if no pattern repeats. You may sharpen persona.line, but keep its number exactly as computed. Save the edited JSON.

3. Render

<skill-dir>/wrapped.sh render "${TMPDIR:-/tmp}/wrapped.json" -o ~/Desktop/agent-wrapped-<year>.mp4

Use ~/Desktop when it exists, otherwise the current directory, unless the user names a place. --format square (1080x1080) for the X or LinkedIn feed; the default is vertical (1080x1920) for Stories, Reels and TikTok.

Report

Give the video path, the headline numbers (hours, sessions, the #1 agent), the persona, and the lessons. Offer to add the lessons to their CLAUDE.md or AGENTS.md. Remind them that the video shows project names and their top phrases, so they should watch it before posting.

Comments

Markdown supported