Reusable AI agent skills for Codex, Cursor, and Claude Code. Install one skill or the whole collection with the Skills CLI
This repository also configures its own agents. See what dotagents tells them →
Skill Codex
Review what a code change could break beyond the diff and prove the main fact that makes it safe. Use only when the user explicitly asks for a blast-radius review, asks what a change could break, or requests extra scrutiny of a suspicious diff.
Skill Codex
Create a concise handoff document so a fresh agent or new session can continue the current work. Use only when the user explicitly asks for a handoff, continuation brief, or context transfer.
Skill Codex
Explain how code, a subsystem, or an architectural flow works. Use only when the user explicitly asks for a code walkthrough, runtime trace, ownership or layering explanation, or architecture critique.
Skill Codex
Keep a reviewable TSV decision trail for long-running or unattended work. Use only when the user explicitly asks for show-me-your-work or a decision log.
Skill Claude CodeCodex
Edit prose to remove common AI-generated patterns and add a natural voice. Use when the user asks to revise, polish, or humanize writing.
Skill Codex
Investigate why code or a design exists using repository history and available contextual sources. Use only when the user explicitly asks about rationale, tradeoffs, regressions, historical constraints, or the origin of a threshold or behavior.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: