skills/init-override/SKILL.md
Create a symlink from AGENTS.md to CLAUDE.md in the current project directory. Use when the user wants to initialise a project to use AGENTS.md as the memory file instead of CLAUDE.md.
npx skillsauth add sofer/.agents init-overrideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a symlink from AGENTS.md to CLAUDE.md in the current project directory, then optionally run /init and sanitise the output.
Check if CLAUDE.md already exists in the current working directory
Create AGENTS.md if it doesn't exist, using the template below
Create the symlink: ln -s AGENTS.md CLAUDE.md
Ask the user if they want to run /init to auto-discover project settings
/init and then proceed to step 5Sanitise the AGENTS.md file by removing or replacing:
CLAUDE.md (replace with AGENTS.md).claude/ pathsEnsure the file header is # AGENTS.md (not # CLAUDE.md or # Project guidance)
Confirm success and show the user the sanitised content
Use this content when creating a new AGENTS.md file (before /init runs):
# AGENTS.md
This file provides guidance for AI agents working with code in this repository.
tools
Check whether Claude and Codex have equivalent access to shared agent resources, skills, hooks, plugins, MCP servers, permissions, startup behaviour, and provider-specific adapter config. Use when comparing agent environments, debugging missing capabilities after restart, or deciding whether to symlink a resource or configure a runtime.
testing
Record substantive skill use in an append-only local log. Use after choosing or invoking a non-system skill for real work, when a skill is inspected but not used, or when a skill fails to apply. Do not use for routine system skills or incidental file reads.
testing
Turn a vague or underspecified request into a self-contained problem statement. Use when the user has a rough idea, when a request would fail if handed directly to an agent, or before non-trivial work that needs shared understanding.
data-ai
Append a one-line learning to ~/.agents/learning-log.md. Use when the user types /learning, or when something genuinely worth remembering surfaced during work and the user confirms it should be captured.