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 instructions/legeling/awesome-codex-pet/agents-mdgit 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/instructions/legeling/awesome-codex-pet/agents-md)<a href="https://agentmods.dev/instructions/legeling/awesome-codex-pet/agents-md"><img src="https://agentmods.dev/badge/instructions/legeling/awesome-codex-pet/agents-md.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 | $0.02130 | $0.02130 |
| Opus 5 | $0.01065 | $0.01065 |
| Sonnet 5 | $0.00426 | $0.00426 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade C, and why
awesome-codex-pet AGENTS.md scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/legeling/awesome-codex-pet/main/scripts/install-pet.sh | bash -s -- <pet-id> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/legeling/awesome-codex-pet/main/scripts/install-pet.sh | bash -s -- <pet-id> How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome Codex Pet Agent Guide
本文件面向在本仓库内工作的 AI coding agents。
默认要求:
- 默认使用中文与用户沟通,除非用户明确要求英文。
- 优先做出可提交的仓库改动,而不是只停留在分析。
- 不要把过程产物混进最终 pet 包。
Pet Skill 版本
$submit-codex-pet是统一投稿入口:区分“请求社区制作”“制作或提交自己的宠物”和“高级 PR”,优先通过 GitHub API 操作,避免为了三个成品文件完整克隆大型素材仓库。$hatch-pet-v1是仓库保留的旧版产线,输出8x9、1536x1872的 v1 spritesheet;维护现有仓库 pet 时使用它。$hatch-pet-v2是从当前 Codex App 内置 skill 同步的 v2 产线,输出8x11、1536x2288的 spritesheet,并要求pet.json.spriteVersionNumber: 2与 16 个环视方向。- 调用时必须显式选择版本。v1 与 v2 都可以收录,但
spriteVersionNumber、图集尺寸和实际行数必须匹配。
1. 项目是什么
awesome-codex-pet 是一个收集和分发 Codex 小宠物的仓库。
它同时承担三件事:
- 收录最终可安装的 pet 成品
- 生成 README 里的动作预览
- 提供无需 clone 仓库的一键安装方式
这个仓库不是宠物制作运行目录本身。制作过程中的参考图、QA 视频、调试文件、临时输出,可以保留在本地,但不应该成为 Git 跟踪内容。
2. 仓库里的真成品
每个 pet 目录只允许保留以下三个文件:
pets/<pet-slug>--<author-slug>/
├── submission.json
├── pet.json
└── spritesheet.webp
必须遵守:
- 目录名格式固定为
pet-slug--author-slug pet.json.id必须与目录名完全一致pet.json.spritesheetPath固定为spritesheet.webp- v1 的
spriteVersionNumber可以省略或设为1,spritesheet.webp必须是1536x1872的 8x9 图集 - v2 必须设置
spriteVersionNumber: 2,spritesheet.webp必须是1536x2288的 8x11 图集,最后两行包含 16 个环视方向 spritesheet.webp必须是最终运行时资源,不要放过程版
不要把这些文件放进 pets/<pet-id>/:
qa/videos/*.mp4contact-sheet.png- 参考图
- layout guides
- prompts
- decoded frames
- repair archive
3. 生成物与来源文件
仓库中允许在本地或 CI 生成的自动生成物主要有:
assets/previews/<pet-id>/contact-sheet.pngassets/previews/<pet-id>/gifs/*.gifREADME.mddocs/zh-CN/README.mdpets.jsoninstall-manifest.json
其中 assets/previews/<pet-id>/ 默认视为本地产物或部署产物,不作为长期 Git 跟踪内容。
这些文件不是手写维护优先项。除非只是极小文案修正,否则应优先修改生成脚本,再重新生成。
相关脚本:
scripts/generate-pet-previews.pyscripts/generate-readmes.mjsscripts/validate-pets.mjsscripts/install-pet.shscripts/install-pet.ps1scripts/install-pet.mjs
4. 本地过程目录
以下内容允许存在于本地,但默认不应被 Git 跟踪:
output/pets/*/qa/- 本地缓存
- hatch-pet 运行目录
如果发现这些内容进入 git status,应优先通过 .gitignore 处理,而不是把它们并入提交。
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.
- 4d ago First seen · 208 lines · 2,130 tokens per session scan C 9c51271f312d
awesome-codex-pet AGENTS.md is an instructions file published in the GitHub repository legeling/awesome-codex-pet (800 stars, last pushed 4d ago), licensed MIT. It adds 2,130 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
codexia AGENTS.md
Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.
rikkahub AGENTS.md
AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.