custom-agent

Installation
SKILL.md
Contains Hooks

This skill uses Claude hooks which can execute code automatically in response to events. Review carefully before installing.

Codex compatibility note:

  • Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author .claude/**; mirrors are generated.
  • Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
  • Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
  • Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
  • Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.

Quick Summary

Goal: Create new custom agents, audit existing agent quality, or enhance agent definitions so each agent is valid, least-privilege, structurally complete, and ready for safe delegation.

Summary: Produce valid agents through the selected mode: Create — clarify → check existing → scaffold → write → validate; Audit — discover → read/parse → validate → report → fix confirmed Errors; Enhance — read → analyze → recommend → apply confirmed changes. Validate frontmatter, tools, structure, and quality score.

Workflow: Detect mode (Create/Audit/Enhance) from $ARGUMENTS → Execute → Validate

Key Rules:

Installs
2
GitHub Stars
3
First Seen
13 days ago