long-horizon

name	long-horizon
description	Use for work too big for one context window: long multi-step tasks, progress lost to compaction or failed retries, work spanning hours or sessions, or when the user says $long-horizon or asks to run a task in verified rounds.

Codex Adapter

Read ../../../.claude/skills/long-horizon/SKILL.md completely and follow it as the canonical workflow for this skill.

• Resolve every relative script, reference, asset, and template path from the canonical skill directory under .claude/skills/long-horizon/.
• Read ../../../.agents/CODEX-SKILL-COMPATIBILITY.md and apply the status and exceptions for this skill.
• Translate Claude Code tool names to the available Codex equivalent as described by the repository AGENTS.md.
• Before any Claude Task, Agent, or Workflow step, confirm that the current Codex session exposes the required multi-agent tools. Do not replace independent review with self-review.
• For long-horizon executor and auditor rounds, call spawn_agent with fork_turns: "none". Send a standalone brief plus state/workspace paths. A positive recent-turn count is an exception only when required data cannot be recovered from those files; record why in the audit log. fork_turns: "all" is not a round default.
• Skill invocation alone does not authorize commit, push, PR, merge, deploy, migration, dependency installation, or another outward action unless that action is the user's explicit request.
• Follow Codex system, developer, sandbox, approval, and tool instructions when they differ from the canonical workflow.
• Keep the canonical Claude skill unchanged unless the user explicitly asks to edit the workflow itself.