A setup guide for preparing a software repository for work shared by human developers and AI coding agents. A repository is the project folder that stores code, documentation, and version history.

Inspecting an existing project and creating or updating AGENTS.md, workflow documentation, harness guidance, execution-plan templates, and related checks.

It creates shared instructions and quality checks so agents know the project rules, planning process, safety expectations, and completion requirements.

repo-init — Skill for Codex by happyfeetw

Install

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.

Any agent

npx skills add happyfeetw/repo-init-skill --skill repo-init

Clone the repo

git clone --depth 1 https://github.com/happyfeetw/repo-init-skill

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/happyfeetw/repo-init-skill/repo-init/github.svg)](https://agentmods.dev/skills/happyfeetw/repo-init-skill/repo-init)

Your own site

<a href="https://agentmods.dev/skills/happyfeetw/repo-init-skill/repo-init"><img src="https://agentmods.dev/badge/skills/happyfeetw/repo-init-skill/repo-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/happyfeetw/repo-init-skill/repo-init"><img src="https://agentmods.dev/badge/skills/happyfeetw/repo-init-skill/repo-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00104	$0.01216
Opus 5	$0.00052	$0.00608
Sonnet 5	$0.00021	$0.00243
Haiku 4.5	$0.00010	$0.00122

Measured 11d ago against content hash bf58a7f0293e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

repo-init 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/init_repo_quality.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

repo-init/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Init

Goal

Set up a repository so AI agents and human collaborators share the same quality workflow: source priority, risk routing, planning, harness gates, report evidence, contract checks, safety rules, and completion standards.

Select template language from the current user-agent conversation language: Chinese conversation -> Chinese templates; English conversation -> English templates. If the user explicitly requests a language, use that language.

Workflow

Inspect the target repository before writing:
- pwd
- git status --short --branch
- existing AGENTS.md, docs/, .github/workflows/, scripts/harness/, package/build files, and module layout
Select language:
- Use zh when the current conversation with the user is primarily Chinese.
- Use en when the current conversation with the user is primarily English.
- Do not ask the user about language unless their request explicitly asks for a different language or the conversation is genuinely mixed.
Identify whether this is:
- a fresh repo with no agent instructions
- a repo with an existing AGENTS.md that must be merged
- a repo that already has harness/docs conventions and only needs alignment
Always scan before writing:
- scripts/init_repo_quality.py --repo <target-repo> --conversation-lang zh --scan
- or scripts/init_repo_quality.py --repo <target-repo> --conversation-lang en --scan
- include --with-harness-skeleton in the scan if the user wants a harness entrypoint created
If the scan finds existing AGENTS.md, related docs, or harness files, stop and ask the user how to proceed unless the user already specified a choice:
- Overwrite: replace generated targets. Use --mode overwrite.
- Merge: preserve existing files, generate .proposed files with --mode propose, then manually merge the standards into the existing repo-specific instructions and docs.
- Skip: leave existing files untouched and report what already exists.
Use the bundled initializer only after the conflict choice is clear:
- Fresh repo: scripts/init_repo_quality.py --repo <target-repo> --conversation-lang <zh|en>
- Merge path: scripts/init_repo_quality.py --repo <target-repo> --conversation-lang <zh|en> --mode propose
- Overwrite path: scripts/init_repo_quality.py --repo <target-repo> --conversation-lang <zh|en> --mode overwrite
- Add --with-harness-skeleton only when the target repo does not already have a harness entrypoint or the user asks for one.
For merge mode:
- Read existing AGENTS.md and related docs.
- Read the generated .proposed files.
- Preserve repo-specific domain, build, test, deploy, security, and workflow rules.
- Add only the missing quality workflow, harness, report, risk routing, and completion standards.
- Remove .proposed files only after their useful content is merged or explicitly rejected.
Adapt placeholders:
- module names
- build/test commands
- docs index path
- runtime/release commands
- contract gate names
- package managers and language-specific checks
Validate with the narrowest available checks:
- git diff --check
- repository docs/harness gate if present
- generated harness skeleton scripts/harness/check.sh docs if created
- skill script dry run or temp-dir run when modifying this skill
Final handoff must include:

files created or updated
selected language and why
whether conflicts were found and whether the user chose overwrite, merge, or skip
whether existing instructions were preserved or proposed separately
validation commands and results
remaining repo-specific placeholders or follow-up work

Read the full file on GitHub · 90 lines

Files

What ships with it

10 files 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.

Changes

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.

11d ago First seen · 90 lines · 104 tokens per session scan A bf58a7f0293e

Subscribe to this mod's changes

repo-init is a skill published in the GitHub repository happyfeetw/repo-init-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 1,216 once invoked, about $0.0005 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 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens