← Blog
explainx / blog

Codex pets complete guide: how to use /pet, hatch-pet, and pick top custom pets (2026)

Deep tutorial for OpenAI Codex desktop pets: Settings, /pet overlay, hatch-pet install, sprite prompts, troubleshooting, security. Plus archetypes for best Codex pets and links to ExplainX prompt kit & hub.

7 min readYash Thakker
OpenAICodexDeveloper toolsAgent skillsUX

MDX restores the committed source plus an HTML comment attribution; plain text bundles the rendered markdown body with the explainx.ai attribution footer.

Codex pets complete guide: how to use /pet, hatch-pet, and pick top custom pets (2026)

Codex pets sit at the intersection of developer-tool UX and agent observability: tiny sprites that react while Codex runs, waits for you, or errors. The feature ships in the OpenAI Codex desktop experience alongside serious knobs—MCP, skills, browser, computer use—but pets punch above their weight for anyone who keeps long threads warm while multitasking.

This is the follow-on to our Codex pets announcement recap. Where that post focused on what shipped, this one is a field manual: settings, commands, hatch-pet install hygiene, art direction, troubleshooting, and a practical answer to “what are the best Codex pets?” without inventing fake rosters.

Fast paths: hatch-pet on ExplainX · copy prompts on ExplainX /generate/codex-pet · browse context on /codex-pets.


Why pets exist (and when they help)

Agentic coding UIs share a nasty failure mode: slow, low-salience feedback. A plan can run for minutes; permissions prompts arrive out of order; background work is invisible unless you obsessively tab back. A persistent, lightweight avatar that mirrors state can beat toast spam when it answers: Is Codex still working? Is it blocked on me? Did the last step explode silently?

That is the same design logic behind status LEDs, CI pills in Slack, and Dynamic Island metaphors—just rendered as a Tamagotchi-class sprite. Leadership commentary on social channels argues pets feel “more useful than they sound”; treat that as product intuition, not peer-reviewed UX research.

When pets hurt: teams allergic to motion, accessibility-sensitive setups, or screen-recorded demos where mascots read as unserious. Codex lets you tuck pets away—they should never be mandatory for power users.


Settings deep dive (Codex app)

OpenAI documents Codex app settings as the home for pet controls under Appearance. The flows you should know:

AreaWhy it matters for pets
GeneralOutput visibility and composer ergonomics influence how often you need peripheral status cues.
AppearanceTheme, accent, fonts—and Pets: choose built-ins or refresh custom pets from your Codex home directory.
Agent configurationInherited from shared Codex config; pets do not replace AGENTS.md discipline.
Integrations & MCPMCP servers share config.toml with CLI; unrelated to sprites but part of the same trust surface.

Command palette: Cmd+K (macOS) / Ctrl+K (Windows) is the fast path for Force Reload Skills, pet toggles mentioned in copy like Wake Pet / Tuck Away Pet, and other Codex commands.

Floating overlay: Pets can stay visible while you context-switch—useful if you batch human reviews while Codex grinds.


Slash commands and composer habits

Baseline:

  • /pet — surface or interact with the pet experience from the composer (exact behavior is versioned—verify in-app help after updates).
  • Wake / tuck — mirrored in Settings for users who prefer clicks over slash syntax.

Creator path:

  • $skill-installer hatch-pet — installs the curated hatch-pet skill from OpenAI’s skills corpus (composer syntax mirrors other Codex skill installers).
  • $hatch-pet … — generation prompts once the skill is live; always reload skills after install.

If a teammate shares a screen recording, standardize language: say “force reload skills” before demoing custom sprites so newcomers do not assume flaky loaders.


hatch-pet: the real extension point

Custom pets are not undocumented graphics APIs. They ride OpenAI’s agent skills system—the same pattern we explain in What are agent skills?.

Authoritative listing + install: hatch-pet on ExplainXsource tree: openai/skillsskills/.curated/hatch-pet

Happy path:

  1. Install hatch-pet using the documented composer installer.
  2. Force Reload Skills from the command menu.
  3. Run a structured prompt (see our prompt kit) so the skill receives art constraints—not vague vibes.
  4. Validate emitted pet.json / atlas conventions in the skill README—avoid hand-editing binary layouts unless you enjoy debugging loaders.
  5. Check sprites into your repo with attribution; treat pet packs like design assets with semver.

Supply-chain hygiene: read SKILL.md, pin revisions, and audit any helper skills that call external image APIs.


What makes a “top” Codex pet

There is no official leaderboard—OpenAI may rotate built-ins. Instead, evaluate pets on readability and state fidelity:

CriteriaGreat petsWeak pets
SilhouetteReads at small sizes; distinct head/body or glyphHair-thin strokes vanish on dark themes
State coverageIdle / busy / blocked / success cues are unmistakableOnly loops idle animation
Color disciplineHigh contrast against Codex chrome; limited paletteNeon gradients that fight UI accents
Motion economyShort loops; no seasicknessExcessive screen shake or particles
Personality copyOne-line flavor text that matches team toneIn-jokes that confuse guests on streams

Documented built-in example: OpenAI’s Codex settings copy cites Seedy with flavor text “A new idea just sprouted from your last prompt.” Use that as a reference for tone—playful, concise, tied to ideation—not as a guarantee every install includes the same roster.

Custom “top picks” by archetype (conceptual):

  1. Minimal blob — lowest art debt, easiest to recolor per brand.
  2. Retro pixel pet — packs nostalgia; watch crispness on HiDPI.
  3. Terminal phantoms — on-the-nose for infra teams; great for internal streams.
  4. Brand mascot (original) — good for startups; avoid copyrighted mascots.
  5. “Finder guy” style experiments — community vibe code; verify licensing before re-sharing publicly (see third-party recaps like 9to5Mac, May 2026).

Art & animation checklist (before you ship a pet pack)

Use this as a pre-flight list when collaborating with design:

  • Canvas & padding: leave transparent margin so sprites do not clip against rounded overlays.
  • States: at minimum align with Codex modes you care about—running, awaiting user, error.
  • Loop timing: 1–3s loops read calmer than sub-second jitter.
  • Accessibility: respect Reduce Motion where the platform exposes it; don’t encode critical status only in shake effects.
  • File hygiene: deterministic naming (idle_01.png, think_loop.png, etc.) saves engineer time.
  • DPI targets: decide whether your pack targets retina-first or scales up from 1x art—document the choice in README.

Troubleshooting

SymptomLikely causesMitigations
Pet never appearsFeature disabled; tucked away; older buildRevisit Appearance → Pets; update Codex; check regional availability notes in official docs
$skill-installer failsSkills path misconfigured; offline restrictionsInspect config.toml MCP/skill entries; verify network; reinstall skill in a clean home dir
Custom pet missing after rebootAssets not in Codex home; loader mismatchRe-run hatch-pet packaging; confirm paths documented in SKILL.md
Animations choppyHeavy atlas; GPU contentionReduce frame count; simplify gradients
Team bans petsCompliance / recording policiesDefault to tucked state; provide pet-free demo profile

Always cross-check developers.openai.com/codex/changelog after an update—pet commands have shifted quickly in early 2026 releases.


Security & compliance notes

Pets are fun; skills remain code + assets:

  • Treat hatch-pet like any curated skill—read prompts it emits, inspect packaged archives, and avoid “pet packs” from anonymous DMs.
  • Red teams: ensure pet overlays do not leak secret snippets in screen shares—same rule as any floating widget.
  • Enterprise: align with branding + accessibility policies; some firms disable decorative motion entirely.

For the broader skills threat model, see Agent skills security.


FAQs (quick)

Do pets improve model quality? No. They change awareness, not reasoning.

Windows vs macOS? Codex targets both; GPU/OS compositor differences mean animation fidelity may not be pixel-identical—test on your fleet.

Can I sell pet packs? Business model is between you and your customers—technically they are assets; legally mind IP and OpenAI mark usage.


Related ExplainX


Sources


Commands, installers, and built-in rosters change with each Codex release. This article reflects May 6, 2026 context—verify Settings, the changelog, and hatch-pet SKILL.md before internal enablement guides go live.

Related posts