From odin
Analyzes a codebase and creates or improves an AGENTS.md file to capture hidden conventions, constraints, and rationale for future agent instances.
How this skill is triggered — by the user, by Claude, or both
Slash command
/odin:initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze this codebase and create or improve an `AGENTS.md` file for future ODIN Code Agent instances.
Analyze this codebase and create or improve an AGENTS.md file for future ODIN Code Agent instances.
AGENTS.md records what needs to be, not what it is. Every entry is a rule, constraint, or obligation a future agent must uphold; it is never a description of the repository's current state. Prescriptive vs. descriptive is the admission gate; everything below refines it.
Write each entry as an imperative or prohibition, paired with why the rule needs to be:
Same fact, but only the normative form carries an obligation.
Everything failing a gate:
Creates, updates, or prunes AGENTS.md with minimal, non-discoverable rules that agents cannot infer from code. Use when setting up agent config or fixing repeated agent mistakes.
Generates and maintains AGENTS.md files for AI agents using shell scripts that detect project structure, extract commands and CI rules, and validate content freshness.
Creates and maintains concise AGENTS.md / CLAUDE.md files for projects. Analyzes toolchain, linters, and conventions to produce minimal agent-facing documentation under 100 lines.
npx claudepluginhub outlinedriven/odin-claude-plugin --plugin odin