sync-configslisted

Audit and sync Claude Code and Codex CLI configurations so both tools share the same instructions, skills, subagents, MCP servers, hooks, and permission intent. Accepts an optional argument naming one skill, agent, or config file to sync just that item without a full audit. Use this whenever the user mentions config drift, syncing/aligning Claude and Codex, AGENTS.md vs CLAUDE.md differences, keeping skills or agents consistent across AI CLIs, or after editing one tool's config and wanting the other to match — e.g. "sync this skill to codex", "I changed my-agent.md, mirror it". Also use when the user asks "are my Claude and Codex setups aligned?" or wants to migrate config from one tool to the other.
supermodo/skills · ★ 1 · AI & Automation · score 77

Install: claude install-skill supermodo/skills

# sync-configs — Claude Code ↔ Codex CLI configuration sync > **Requires:** the sibling `protocols` skill (shared protocol masters); uses `skills.config.json` when present. Missing protocols → tell the user to install the full supermodo package. Audit every configuration surface shared between Claude Code and Codex CLI, report drift, propose per-item sync actions, apply only what the user approves, then have the *opposite* provider adversarially verify the result. Never commit or push — leave all changes in the working tree. ## Modes - **Full audit** (no argument) — run the whole Workflow below, every surface, both scopes. - **Targeted sync** (argument given) — the user named one thing: a path (`.claude/agents/reviewer.md`, `.agents/skills/tests/`, `.mcp.json`), a bare name (`the tests skill`, `reviewer agent`), or a surface (`mcp`, `hooks`). Sync only that item; do NOT scan or report on anything else. See "Targeted mode" below. ## Why this skill exists Both tools configure the same concepts (instructions, skills, subagents, MCP servers, hooks, permissions) in different files and formats. Edits land on one side and silently drift from the other. This skill makes drift visible and repairable in one pass. The two vendors converged on one shared standard: the **Agent Skills spec** (`SKILL.md` folders) and the neutral **`.agents/skills/`** directory, which both tools read. Everything else requires translation (JSON ↔ TOML) or semantic mapping (permission models).