Claude Pokémon

Add a pet to your Claude Code terminal

·

source at a5c6463

·

No license

A pixel Pokémon that lives at the right edge of the band above the prompt

What this mod can do

  • Reviewed at commit a5c6463
  • Connects to the internet
  • Reads environment variables
  • Sees each change to /config and can block or rewrite it
  • Sees each prompt you send and can change or drop it
  • Sees each tool call before it runs and can block or change it
  • Can approve or deny each tool call before Claude Code asks you
  • Sees each subagent before it starts and can stop it or pick its model
  • Also uses skill.prompt, which this page doesn't describe yet
9 more things it can do
  • Reads your settings
  • Reads your prompt as you type
  • Remembers data between sessions
  • Adds slash commands
  • Adds the /pokemon command
  • Lists running subagents
  • Lists the slash commands you can run
  • Runs on a timer
  • Runs on Claude Code hooks, such as session start
Good to know (3)
  • Needs a truecolor terminal such as iTerm2, Ghostty, kitty or WezTerm
  • In iTerm2, set CLAUDE_CODE_FORCE_TERMINAL_IMAGES to 1 in the env block for pixel images
  • Food and happiness drain over hours; with both empty for 3 hours of open time, the mon faints
Are mods safe?

Preview

Terminal

[-] ▄▄▄▀▀▀▀▀▄▄▄▄ ▀▀ ▀ ▀ ▄▀ ▀▄ ▀▀▀▀ ▀▀▀▀▀ ▀▀▀▀▀▀▀▀▀▀▀▀ ▄▄▀▀ ▀▀▀ ▀▀▀▄ Lv 5 ▀▀▀▀▀▀ ▀▀▀ ▀ ●●●●○ ▀ ▀▀ ♥♥♥♥♡

Claude Desktop

Claude Pokémon in Claude Desktop

What it does

A pixel Pokémon above the prompt that reacts to Claude's tools, subagents and questions, levels up as turns finish, and needs feeding and petting.

What you see
A pixel mon at the right of the band above the prompt
Works in
Terminal and Claude Desktop
Slash commands
/pokemon
Uses your tokens
No
Changes files
Nothing
Network access
Gen 2 to 5 sprites from vscode-pokemon, on /pokemon new
Reviewed commit
a5c6463
Preview recorded with
Claude Code 2.1.296

How it works

  1. Pick a starter with /pokemon charmander, or Bulbasaur, Squirtle or Pikachu
  2. Watches tool calls, subagents and permission prompts while Claude works
  3. Shows a bubble per tool, a Poké Ball per subagent, and a red ! when Claude needs you
  4. Answered turns earn XP and evolutions; wild mons show up for you to /pokemon catch

Common questions

How do I add a pet to Claude Code?

Install this mod with claude plugin marketplace add dgokcin/claude-pokemon-mod and claude plugin install pokemon@claude-pokemon, then pick a starter such as /pokemon charmander. It runs in the terminal or the Desktop app's Code tab.

Can it show me when Claude Code is waiting for my answer?

Yes. The mon stops, faces you and shows a red ! for questions, plan approvals and permission prompts until you answer. Under an organization policy that blocks classic.* events, the ! still shows for questions and plan approval but not for permission dialogs.

What happens if I ignore the pet?

With both meters empty for 3 hours of open session time it faints. /pokemon revive heals it in 5 minutes; left fainted for 24 more hours it runs away, and you can catch it again in the wild. With /pokemon nuzlocke on, a fainted mon is gone for good, and /pokemon needs turns the meters off.

Does it work in VS Code or on mobile?

No. The VS Code extension and the mobile app have no band to draw in, so the mon only shows in the terminal and the Desktop app's Code tab.

More like this

Deck in Claude Desktop

A cockpit for Claude Code: plan bars and subagent strips, context, usage limits with reset countdowns and burn rates, spend, the model route and a pet. Six bar styles, three collapsed looks. CLI and Desktop.

⎿ agent-profiler: Agent Profiler pane opened (shown in the terminal and the desktop app). ╭────────────────────────────────────────────────────────────────────────────────────────────────✕─╮ │ 125ms agent time · 1 turn(s) │ │ model ███████░░░░░░░░░░░░░ 33% │ │ tools ░░░░░░░░░░░░░░░░░░░░ 0% │ │ subagents ░░░░░░░░░░░░░░░░░░░░ 0% │ │ engine/other █████████████░░░░░░░ 67% │ │ │ │ Running │ │ idle │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ ⚠ agent-profiler: ⏱ model 33% · tools 0%

Execution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export

Opus 4.8 │ main │ app │ ▓▓░░░░░░░░ 44k/200k │ $0.41

Catppuccin Frappé-themed status line with model, git branch and dirty flag, folder, a block context bar, and session cost.

Opus 4.8 high ✦ │ ctx 22% │ app (main) │ PR #1287 ● │ $0.41 · 10m +128 -34 Session ● ● ● ● ● ● ● ● ○ ○ ○ 74% left Resets in 2h 6m Weekly ● ● ● ● ● ● ● ● ● ● ○ 93% left Resets in 2d 0h Fable ● ● ● ● ● ● ● ● ● ○ ○ 85% left Resets in 2d 0h ◐ Read:index.ts ✓ Read×1 ✓ Bash×1 ✓ Edit×1 ✓ Grep×1 ◐ code-reviewer Review the change for regressions

A header with model, context and burn rate per hour, then live tool and agent activity parsed from the session transcript.

Opus 4.8 │ ✍️ 22% │ app (main) │ ● high current ●●○○○○○○○○ 26% ⟳ 6:59pm weekly ○○○○○○○○○○ 7% ⟳ aug 1, 5:52pm

Model, context, directory and branch up top; five-hour and weekly quota as dot bars with reset times underneath. Flags --dangerously-skip-permissions with a lightning bolt. By Kamran Ahmed of roadmap.sh.

Opus 4.8 | app@main | 44k/200k (22%) | effort: high | 5h 26% @18:59 | 7d 7% @Sat Aug 1, 17:52

Model, directory and branch with diff counts, context tokens, reasoning effort, and five-hour and seven-day limits from Claude Code's own rate-limit data, with the usage API as fallback. Checks for new versions of itself once a day.