By cleggypdc
Collect usage telemetry and session metadata across Claude Code lifecycle events, enabling monitoring of session activity and pending skill notifications via Python collectors run with uv.
A Claude Code plugin that launches the original DOOM (rendered in ASCII) while Claude is thinking.
https://github.com/user-attachments/assets/effe9689-7b77-473e-a900-d26da3d83b9a
The game uses doom-ascii, a source port of the original DOOM engine that renders to ASCII block characters in your terminal. It plays the shareware WAD (Episode 1: Knee-Deep in the Dead).
git clone https://github.com/cleggypdc/doom-claude-code-plugin.git
Then use the wrapper script which transparently runs Claude inside tmux (required for the overlay):
alias claude='~/doom-claude-code-plugin/scripts/claude-wrapper.sh'
claude
Or if you're already in tmux, you can use the plugin directly:
claude --plugin-dir ./doom-claude-code-plugin
First run automatically downloads the doom-ascii binary and the freely distributable shareware WAD (~5MB total).
tmux (for overlay popup — falls back to running without overlay if unavailable)curl and unzip| Key | Action |
|---|---|
| Arrow keys | Move |
, / . | Strafe |
| Space | Fire |
| E | Use / Open doors |
] | Sprint |
| 1-7 | Weapon select |
| Event | Action |
|---|---|
SessionStart | Downloads doom-ascii + WAD (first run only) |
UserPromptSubmit | Launches DOOM as tmux popup overlay |
Stop | Dismisses the DOOM popup |
SessionEnd | Kills DOOM |
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub cleggypdc/doom-claude-code-pluginPermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment