Home / adalbertocv / agentify-repo · GitHub

agentify-repo SKILL.md skillA

agentify-repo from adalbertocv/agentify-repo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add adalbertocv/agentify-repo/agentify-repo@git:20261008.94938bb

Pins git:20261008.94938bb in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
adalbertocv/agentify-repo
Path
SKILL.md
Versions recorded
4
Latest version
git:20261008.94938bb, committed Oct 8, 2026
First version recorded
Oct 4, 2026
Size
9,284 bytes
Repository stars
4
License
MIT

Use when asked to prepare, onboard, or "agentify" a repository for AI coding agents; to create, update, regenerate, or audit AGENTS.md, CLAUDE.md, GEMINI.md, .cursorrules, or copilot-instructions; when agent instruction files are missing, stale, bloated, or contradict each other or the code; or when asked (or passed `--brain`) to set up a context brain, a docs/agents documentation structure, or routers that save agent context.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agentify Repo

## Overview

An AGENTS.md is worth only what an agent **cannot cheaply discover by itself**: commands that verifiably work, traps, boundaries, and decisions that are invisible in the code. Folder listings, dependency lists and lint rules are noise: the agent can read those itself.

**Core rule:** every statement in the file has a known source. Commands carry a status from verification. Any other claim is tagged in its text: *verified*, *from config*, *from code*, *from docs*, *from tests*, or *from user*. `check_agents_md.py` warns about untagged bullets. Leave out anything that has none of these sources.

Scripts live in `<skill-dir>/scripts/`. Run them with `python`, or with `py` on Windows when `python` is a Store alias. All of them are stdlib-only and accept `--help`.

In Codex, invoke this skill with `$agentify-repo` or select it with `/skills`. Use the Codex workflow below when running in Codex or when the user requests Codex-only output; otherwise preserve the existing Claude-compatible workflow. If the target is unclear, ask which agent the docs should support.

## Procedure
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add adalbertocv/agentify-repo/agentify-repo@sha256:cc3c054cc5fc26d3

The line at the top of this page pins the label git:20261008.94938bb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_62ypb4uio7find47.svg)](https://markdownregistry.com/a/art_62ypb4uio7find47)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Oct 4, 2026 and Oct 8, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261008.94938bb latest2026-10-08 94938bb 9,284 BA view · diff
git:20261006.e209ba72026-10-06 e209ba7 6,998 BA view · diff
git:20261006.ae944492026-10-06 ae94449 5,563 BA view · diff
git:20261004.ed5dc902026-10-04 ed5dc90 4,994 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9284 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

adalbertocv/agentify-repo · 4 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_62ypb4uio7find47
GET https://markdownregistry.com/api/v1/resolve?ref=adalbertocv/agentify-repo/agentify-repo
GET https://markdownregistry.com/api/v1/blob/cc3c054cc5fc26d319883d74c193ec9414a4d46f832d6923ff6b3664f0ede53e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.