Pet Pepper CLI · v0.1
Docs
The Pet Pepper CLI lets you install, browse, and submit Codex pets from your terminal. Authentication uses OAuth 2.0 + PKCE through Clerk, and tokens persist in your OS keychain.
Quick start
Follow this checklist to get a pet installed, visible in Codex, and connected to the desktop app. No account required to install. Sign in only when you submit.
- 1
Install a known pet
Start with Boba so you have a real pet folder to select in Codex.
You should see
~/.codex/pets/boba/withpet.jsonand a spritesheet. - 2
Initialize desktop and hooks
Run the full setup when you want the floating desktop mascot and agent activity hooks.
Pet Pepper downloads the desktop app, starts it, and wires supported agents for
/petdex. - 3
Select the pet in Codex
Open Codex, go to Settings → Appearance → Pets, choose Boba, and click Select.
Use
/petinside Codex to wake the pet or tuck it away. - 4
Verify the setup
Run diagnostics if the pet does not appear, or type
/petdex statusinside a supported agent after hooks are installed.The doctor reports any missing binary, hook, token, or pet folder with a concrete fix.
petdex submit.Install
The CLI runs on Node 20+ (or Bun). Pick the workflow that fits you. Both are equivalent in capability and persistence.
Casual / one-off
Use npx. No setup, package is cached after first run.
Power user
Install globally for instant invocation and easier muscle memory.
Auth persistence is identical in both. Tokens live in your OS keychain (macOS Keychain, Windows Credential Manager, Linux Secret Service) under the service name petdex-cli. Even if npx clears its package cache, your session survives.
Authenticate
Sign in once, then any command that needs auth, such as submit, works seamlessly.
The flow is OAuth 2.0 + PKCE: the CLI opens your browser, you sign in with Clerk on accounts.pet-pepper.example, and the browser redirects to a one-shot localhost listener with the authorization code. The CLI exchanges it for a token set and stores it in the keychain. No secrets touch disk.
Other auth commands:
Commands
The CLI covers the full lifecycle: discover, install, hatch, publish, plus the desktop app and agent hooks. All commands accept --help.
petdex list
Print every approved pet with credit. Useful for discovery before installing.
petdex install [slug]
Drop a pet into ~/.codex/pets/[slug]/. Equivalent to curl -sSf https://pet-pepper.example/install/[slug] | sh.
petdex submit [path]
Publish your pet(s) to the gallery. The CLI accepts three shapes:
- Single folder:
petdex submit ~/.codex/pets/boba - Single zip:
petdex submit ~/Downloads/boba.zip - Bulk:
petdex submit ~/.codex/pets: every direct subfolder is treated as its own pet
Bulk mode shows a progress spinner per pet and a final summary of failures. Slugs auto-deduplicate so you will not hit a slug-taken bounce.
petdex login / logout / whoami
See the Authenticate section above.
Desktop app
Pet Pepper Desktop is a floating mascot that lives on top of your workspace and reacts to your coding agent tool calls. macOS today, Linux and Windows soon. See /download for the visual tour.
petdex install desktop
Fetches the latest binary from GitHub Releases for your platform and drops it at ~/.petdex/bin/petdex-desktop. The CLI strips the macOS quarantine attribute so the app opens without a Gatekeeper prompt.
petdex hooks install
Wires the desktop app into your coding agents so the pet animates as you work. Picks the agents present on your machine and writes hooks for each:
- Claude Code:
~/.claude/settings.json - Codex CLI:
~/.codex/hooks.json - Gemini CLI:
~/.gemini/settings.json - OpenCode:
~/.config/opencode/plugins/petdex.js
Tool events map to pet states: tool.before → running, tool.after → idle, session.end → waving, session.error → failed. Each hook POSTs to the local sidecar at http://127.0.0.1:7777/state.
petdex desktop <start | stop | status>
Manage the running pet. start spawns it detached (PID at ~/.petdex/desktop.pid, log at ~/.petdex/desktop.log). stop sends SIGTERM. status reports running, stopped, or stale.
petdex up / down / toggle
One-shot wake/sleep for the mascot. up enables hooks AND launches the desktop. down disables hooks AND stops the desktop. toggle flips between them based on current state. That is what the /petdex slash command runs from inside your agent.
/petdex (slash command)
Once petdex hooks install has run, every supported agent (Claude Code, Codex, Gemini, OpenCode) gets a /petdex command in its picker. Type it inside the agent and the mascot wakes or sleeps without leaving the chat:
/petdex: toggle (wake if asleep, sleep if awake)/petdex up: force-wake/petdex down: force-sleep/petdex status: show whether hooks are enabled/petdex doctor: diagnose install + agent wiring
petdex hooks (kill-switch)
Even with hooks installed, you can pause them without touching your agent settings. petdex hooks off drops a flag file at ~/.petdex/runtime/hooks-disabled; every installed hook checks for it first and exits 0 immediately. petdex hooks on removes the file. Useful when a sidecar has gone weird and you do not want stray curls in your agent log.
petdex hooks uninstall
Reverses hooks install: removes the petdex entries from each agent config (preserving your own hooks), deletes the /petdex slash command files, and removes the OpenCode plugin. Pass --remove-token to also drop the auth token at ~/.petdex/runtime/update-token.
petdex doctor
Diagnostic. Verifies binary, sidecar bundle, sidecar reachability, pid file format, token mode, kill-switch state, hooks installed in each agent, Codex codex_hooks feature flag, and usable pet count. Each failed check ships an actionable hint.
petdex update
Compares your installed version against the latest GitHub Release tag and downloads it if newer. If the desktop app was running, it stops it, swaps the binary, and restarts. Pass --force to re-download the same version.
7777. Anything that can curl + read the per-session token at ~/.petdex/runtime/update-token can drive the pet. The token rotates every sidecar boot and lives at mode 0600, so only your user can read it. Browsers and remote sites cannot:T="$(cat "$HOME/.petdex/runtime/update-token")"
curl -X POST http://127.0.0.1:7777/state \
-H "Content-Type: application/json" \
-H "X-Petdex-Update-Token: $T" \
--data-raw '{"state":"waving"}'Distribute your pets
Once you have hatched a pet inside Codex, sharing it takes one command. Here's the full lifecycle:
- Create. In Codex Desktop, install the Hatch Pet skill and run
/pet. Codex generates the spritesheet and pet.json into~/.codex/pets/[slug]/. Full tutorial at /create. - Sign in.
npx petdex loginif you have not. - Submit.
npx petdex submit ~/.codex/pets/[slug]. Or bulk all at once with the parent dir. - Wait for review. Submissions land as “pending” in the admin queue. You will receive a Resend email when approved or rejected (if rejected, the reason is included).
- Anyone can install your pet. Once approved, share
npx petdex install [your-slug]with anyone. They get your pet in their~/.codex/pets/instantly.
Validation rules
The server enforces these rules; the CLI checks locally too.
pet.jsonandspritesheet.webp(or.png) must be at the root of the folder/zip.- Spritesheet ≥ 256×256. Recommended 1536×1872 (8×9 frame grid).
- Rate limit: 10 submissions / 24h per user. Admins bypass.
- Slugs auto-deduplicate (
boba→boba-2→boba-3→ …). You always get a successful submission. - Identity (userId, email, credit) comes from the verified OAuth token. Never trusted from request body.
Failure modes
| Symptom | Cause | Fix |
|---|---|---|
| Not signed in | No tokens or session expired | petdex login |
| presign 401 | Bearer rejected by Clerk userinfo | petdex logout then petdex login |
| presign 429 | 10/24h rate limit hit | Wait 24h or open a submit-fallback issue |
| register 400 invalid_spritesheet | Sprite < 256×256 | Regenerate at 1536×1872 |
| register 400 missing_field | Folder missing pet.json or spritesheet | Inspect folder contents |
| R2 PUT 403 | Presigned URL expired (60s TTL) | Retry: CLI auto-presigns fresh URLs |
Agent-first usage (Skill)
Pet Pepper ships a Claude Code / Codex / Cursor compatible skill at .claude/skills/petdex/SKILL.md. Compatible agents load it automatically and learn when and how to call the CLI on your behalf.
What this enables
- Say “install something cozy for my Codex” in any agent tool. It runs
petdex list, suggests Boba/Boxcat, installs your pick, and reminds you to activate via Settings → Appearance → Pets. - Say “share all my pets”. Agent runs
petdex loginif needed, thenpetdex submit ~/.codex/pets, surfaces the bulk summary. - Say “how do I make my own?”. Agent walks you through Codex Desktop → Hatch Pet skill →
/pet→petdex submit.
How to enable it
If you use Claude Code, save the skill globally so every project has it:
Other agent tools can load the same SKILL.md from the repo. The file is plain markdown. No agent-specific syntax beyond allowed-tools.
Build your own skill on top
The CLI is the executable surface; the skill is the cognitive one. If you build a derivative skill (for example, one that auto-tags new pets or curates a daily digest), you can use the Pet Pepper skill as a reference. Read it directly:
Configuration
The CLI ships with sensible defaults pointing at production. You only need to override env vars if you are testing against a non-production deployment.
PETDEX_URL: base URL, defaulthttps://pet-pepper.exampleCLERK_ISSUER: OAuth issuer, defaulthttps://clerk.pet-pepper.exampleCLERK_OAUTH_CLIENT_ID: public client id (baked into the CLI binary)
Contribute
- PRs welcome at henryjing96/pet-pepper-platform
- Bug reports and feature requests: open an issue
- Sponsor on GitHub Sponsors if Pet Pepper saves you time.