optimize-context

name

optimize-context

description

Reduce per-turn context/token cost (the always-loaded weight: CLAUDE.md kernel, MEMORY.md index, the deferred MCP tool-name list, MCP instruction blocks, and the injected available-skills list) — then propagate the portable, generic wins up to the claude-starter template so future repos start lean. Use when the user says $optimize-context, "cut context", "reduce tokens", "trim the kernel", "what's loading every turn", "make this leaner", or asks to push an optimization to the starter. Pairs with sync-starter (which carries the push mechanics).

Codex Adapter

Read ../../../.claude/skills/optimize-context/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/optimize-context/.
• 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.
• 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.