What is claude-pokemon-pet CLAUDE.md?

Development instructions for a Claude Code plugin that displays a floating Pokémon pet reacting to session events. They define its architecture, shell compatibility, runtime files, dependencies, and testing rules.

Use them when developing, testing, or reviewing the Pokémon pet plugin, especially its event hooks, state processing script, renderers, data packs, and shell scripts.

They keep the event-processing core separate from display code and protect the plugin from breaking on macOS, changing its own files at runtime, or failing silently in hook execution.

How junoh-bg/claude-pokemon-pet configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to junoh-bg/claude-pokemon-pet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/junoh-bg/claude-pokemon-pet/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/junoh-bg/claude-pokemon-pet

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/junoh-bg/claude-pokemon-pet/claude-md/github.svg)](https://agentmods.dev/instructions/junoh-bg/claude-pokemon-pet/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/junoh-bg/claude-pokemon-pet/claude-md"><img src="https://agentmods.dev/badge/instructions/junoh-bg/claude-pokemon-pet/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/junoh-bg/claude-pokemon-pet/claude-md"><img src="https://agentmods.dev/badge/instructions/junoh-bg/claude-pokemon-pet/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,962 This file is loaded in full into every session.

When invoked 1,962 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01962	$0.01962
Opus 5	$0.00981	$0.00981
Sonnet 5	$0.00392	$0.00392
Haiku 4.5	$0.00196	$0.00196

Measured 10d ago against content hash 8ae2b7f9b685, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-pokemon-pet CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — claude-pokemon-pet

A Claude Code plugin: floating Pokémon pet that reacts to session hooks. v2 roadmap: docs/superpowers/specs/2026-07-13-v2-roadmap-design.md.

Architecture (v0.4.0+)

Hooks write events → scripts/pet-core.sh (bash+jq) reduces them to ~/.cache/claude-pokemon-pet/resolved.json → renderers are pure views. Never put game logic (leveling, evolution, gacha, i18n data) in a renderer; never make the core depend on a renderer. Franchise data lives in JSON packs (data/<franchise>/pack.json).

Hard rules

bash 3.2 (macOS /bin/bash): no mapfile, ${var,,}, associative arrays.
Hook path is sacred: pet-core.sh event * must always exit 0 and stay silent, whatever the state of PATH or the cache. Anything before the case dispatch runs unguarded — keep it silent too (2>/dev/null).
Zero new runtime deps for the core (jq + gifsicle only). Terminal renderer (Phase 2) may use pure-stdlib Python 3.
Runtime writes go only to ~/.cache/claude-pokemon-pet/; never the plugin dir.
BSD/GNU date portability: date -v-1d +%F 2>/dev/null || date -d yesterday +%F.
Conventional commits, colon separator.

Testing

bash tests/run.sh — zero-dep harness, must pass before every commit.
Tests are hermetic: throwaway $HOME, and env seams PET_TODAY, PET_YESTERDAY, PET_NOW, PET_SEED, PET_LANG. Never let a test touch the real cache or depend on host locale — this dev machine is Korean macOS; anything reading system language will return ko.
Real hook payload fixtures live in tests/fixtures/ (captured via a probe project, see docs/notes/2026-07-13-posttooluse-payload.md).
Manual overlay QA: toggle the installed plugin off first (~/.claude/plugins/marketplaces/claude-pokemon-pet/scripts/claude-pokemon-pet off), launch the dev overlay (nohup osascript -l JavaScript scripts/pet-overlay.js "$PWD" &), verify, kill it, toggle the installed one back on.

Code review

Reviewer: code-reviewer agent (model: sonnet), on the branch diff.
Checklist: bash-3.2 compat; behavior parity vs v1 formulas; hook-path exit-0/silence; atomic writes (mktemp+mv) for JSON state; RESOLVE_JQ math vs golden tests; test hermeticity; stale refs after file moves.
Loop until PASS; fix ALL findings including Minor.

Read the full file on GitHub · 130 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 130 lines · 1,962 tokens per session scan A 8ae2b7f9b685

Subscribe to this mod's changes

claude-pokemon-pet CLAUDE.md is an instructions file published in the GitHub repository junoh-bg/claude-pokemon-pet (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,962 tokens to every session, about $0.0098 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code claude-code-plugin claude-code-plugins macos pokemon

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-pokemon-pet: Instructions file for Claude Code