Agent Codex
Agent definition files installed into /.agents/agents/ by bin/install.mjs. /.claude/agents is a directory pointer to that folder. Each .md file defines a named subagent: its description (shown in the Claude Code UI), allowed tools, and behavioral instructions.
Agent Codex
Use PROACTIVELY for ALL code generation — features, fixes, refactors, hooks, automation, and any task that produces code. Links the project review contract, CODERULES, enforcer, and rules map; task-local discovery; gotchas with clear checks and review evidence.
Agent Codex
Use this agent for comprehensive code quality reviews across multiple files.
Agent Codex
Use this agent when you need to create git commits, stage changes, or organize multiple file changes into atomic commits. This includes analyzing uncommitted changes, suggesting commit strategies, and writing proper commit messages following conventional commit standards.
Agent Codex
Primary handler for one GitHub issue action per spawn on a work-stream: open an epic, file a sub-issue, update status in place, refresh the epic checklist, or close a sub-issue. Spawn with one action plus the issue-candidate or issue number it needs; loads the issue-tracker skill; returns affected issue numbers and…
Agent Codex
Fresh-context validator for workflow-generated plan packets. Use after a plan packet is written under docs/plans/ / to verify source accuracy, completeness, TDD readiness, scope control, handoff quality, and no invented repo behavior. Read-only; never edits files.
Agent Codex
Optional agent that drafts factual pull request descriptions and comments from the current diff and validates each statement against the master review guides.
Agent Codex
Standing reviewer for a whole session, or for a shared session and the subagents it spawns. Consulted before committing to a multistep plan, once the session believes the work is complete, before any commit is executed, when the same failure repeats, or when reconsidering the chosen approach. Returns one of four…
Agent Codex
Authors a skill package — SKILL.md plus companion files — to skill-builder conventions: hub layout, trigger-catalog description, deterministic work shipped as scripts and task-seed lists. Triggers: author a skill, write a SKILL.md, skill-writer-agent, delegate skill file authoring, produce skill package files.