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.
npx agentmods add skills/legeling/awesome-codex-pet/submit-codex-petnpx skills add legeling/awesome-codex-pet --skill submit-codex-petgit clone --depth 1 https://github.com/legeling/awesome-codex-petWrote 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.
[](https://agentmods.dev/skills/legeling/awesome-codex-pet/submit-codex-pet)<a href="https://agentmods.dev/skills/legeling/awesome-codex-pet/submit-codex-pet"><img src="https://agentmods.dev/badge/skills/legeling/awesome-codex-pet/submit-codex-pet.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00079 | $0.01890 |
| Opus 5 | $0.00039 | $0.00945 |
| Sonnet 5 | $0.00016 | $0.00378 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
submit-codex-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit Codex Pet
Use GitHub APIs or an authenticated GitHub CLI by default. Do not make the user clone the full catalog unless API-based contribution is unavailable and they approve the fallback.
Choose the route
- Request: the user wants the community or maintainers to make a pet. Search for duplicates and create a
[Request]issue containing<!-- pet-flow: request -->; do not make or submit the pet in this route. - Submission: the user owns the submission and wants AI to create or finish it from references, or already has a spritesheet, pet folder, or finished assets. Complete production as needed, validate the result, then open a focused pull request through the GitHub API.
- Blocked submission: use only after trying the recovery steps below and receiving the user's approval. Create a concise
[Submission]issue containing<!-- pet-flow: submission -->when a duplicate needs maintainer judgment, required review files cannot be made accessible, or GitHub authorization remains unavailable. - Advanced PR: the user explicitly prefers Git, GitHub, or Codespaces. Follow
CONTRIBUTING.md; use a sparse, blob-filtered clone when a local checkout is needed.
Repository: https://github.com/legeling/awesome-codex-pet
Request workflow
- Read
pets.json,collections.json, and open pet issues through GitHub. Search canonical identity, localized names, franchise, author, and tags. - Ask for the character or concept, original work, V1/V2 preference, references, visual direction, naming language, and any available attribution or usage terms.
- Classify reference availability before creating the issue:
- A real pet, original character, avatar, or other appearance-specific request requires at least one image attachment or public image URL that maintainers can open.
- A known canonical character may use an official character or source page when that page clearly establishes the appearance.
- An appearance-free concept may proceed without an image only when the issue explicitly says it has no fixed visual appearance. A local filename, filesystem path, image visible only in the current chat, or prose saying that a photo exists is not an accessible reference.
- When creating an issue through the GitHub API, do not imply that a local or chat image was uploaded. If the available GitHub capability cannot upload it, pause issue creation and ask the user to attach the image through GitHub, then verify that the issue body or comment contains a viewable attachment URL before treating the request as complete.
- Keep reference authorship and source notes truthful, mark the requested output as non-commercial, and never imply that a request is accepted or scheduled.
- Follow
.github/ISSUE_TEMPLATE/pet-request.yml. Include the duplicate result and unresolved questions. - Create the issue and return its URL. Repository automation manages type, status, version, and category labels.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 78 lines · 79 tokens per session scan A 7535571b7e67
submit-codex-pet is a skill published in the GitHub repository legeling/awesome-codex-pet (827 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,890 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
agentmail
Use when an agent needs AgentMail CLI email inboxes.
mcporter
List, auth, and call MCP servers/tools from the terminal.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".