Repo codex bootstrap

Skill yangshu2087/Codex/.agents/skills/repo-codex-bootstrap

Add or refresh repository-level Codex scaffolding such as .codex/config.toml and AGENTS.md. Use when a repo needs lightweight Codex defaults, repo-specific instructions, or a repeatable project bootstrap.From its SKILL.md

Install

npx -y skills add yangshu2087/Codex --skill repo-codex-bootstrap

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, 288 tokens by cl100k_base, as published. Nobody here has run it

Repo Codex Bootstrap

Use this skill when a repository is missing Codex project scaffolding or its local instructions have drifted.

Workflow

Inspect the repository before writing anything:
- git status --short
- top-level files and directories
- existing .codex/ or AGENTS.md
Infer the repository purpose from local files, not from the directory name alone.
Add the smallest useful project config:
- usually approval_policy = "on-request"
- usually sandbox_mode = "workspace-write"
- only add extra keys when the repo clearly needs them
Write AGENTS.md with repo-specific rules:
- what the repo is for
- what not to do here
- how to verify changes in this repo
Avoid copying a generic wall of text into every repo. A short, accurate repo guide is better than a long template.
After changes, rerun the narrowest relevant verification commands and report the exact files added or updated.

Team conventions

Shared team skills live in /Users/yangshu/Codex/.agents/skills.
Project-level instructions should complement ancestor instructions, not restate them verbatim.
When a rule applies to every repo, prefer the shared ancestor AGENTS.md. Use repo AGENTS.md only for local specifics.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most project setup skills give in 288 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

Ask one question at a timein 29 of 999, across 28 files
Detect the package manager from lockfilesin 28 of 999, across 9 files
Present findings to the userin 26 of 999, across 5 files
Explore current repo statein 24 of 999, across 3 files
Update the agent skills block in place if it existsin 24 of 999, across 3 files
Install husky lint-staged and prettierin 23 of 999, across 4 files
Create the lintstagedrc filein 22 of 999, across 3 files
Commit all changed filesin 22 of 999, across 3 files
Run lint-staged to verify it worksin 22 of 999, across 3 files
Create the husky pre-commit filein 21 of 999, across 2 files
Create a prettierrc file if missingin 21 of 999, across 2 files
Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

Infer repository purpose from local files only
Add the smallest useful project config
Write repo-specific rules into AGENTS.md
Rerun narrowest verification commands after changes
Prefer shared ancestor AGENTS.md for global rules

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.