Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add SHIN620265/claude-petnpx agentmods add plugins/shin620265/claude-pet/petgit clone --depth 1 https://github.com/SHIN620265/claude-petGrade A, and why
claude-pet 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 2d 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "claude-pet",
"displayName": "Claude Desktop Pet",
"version": "1.5.0",
"description": "A desktop companion (Windows) that watches your Claude Code sessions and tells you - with status cards and a soft chime - when Claude is thinking, needs your input, or is done - and flags a card that's still running a background task. Hover a card to see everything.",
"author": { "name": "Peng Shen" },
"homepage": "https://github.com/SHIN620265/claude-pet",
"repository": "https://github.com/SHIN620265/claude-pet",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 command, 10 hooks travel with it, and installing the plugin installs all of them — 9 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command my-pet A 9 tokens
- Hook Notification A not measured
- Hook SessionEnd A not measured
- Hook UserPromptSubmit A not measured
- Hook PermissionRequest A not measured
- Hook SessionStart A not measured
- Hook PostToolUseFailure A not measured
- Hook PostToolUse A not measured
- Hook ElicitationResult A not measured
- Hook PermissionDenied A not measured
- Hook Stop A not measured
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.
- 2d ago First seen · 12 lines scan A 233791f7ff4c
claude-pet is a plugin published in the GitHub repository SHIN620265/claude-pet (3 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
neonwatty-plugins marketplace
Job Apply plugins for Codex and Claude Code by Jeremy Watt.
job-apply-plugin
AI-powered job application assistant for Claude Code and Codex covering LinkedIn, Greenhouse, Ashby, Lever, Rippling, and Workday.
agentcall
Join video meetings (Google Meet, Zoom, Teams) as an AI bot with voice, avatar, screenshare, and real-time transcription. Any AI agent can participate in calls via voice conversation, TTS, and meeting intelligence.
jobxhunter
Build a master profile from your own files, tailor ATS-safe CVs to any job description, source live UK and Canada roles, write cover letters, and track every application.
soheil-jobxhunter marketplace
Job-hunting tooling for the UK and Canada: profile intake, ATS-safe CV tailoring, sourcing, cover letters, and application tracking.
agentrq-workspace
Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.