ultracode-editlisted

Safely modify an initialized UltraCode repository configuration and its managed Codex or Claude Code projections. Use when the user explicitly invokes `$ultracode-edit`, wants to change project AI rules, commands, control visibility, status persistence, model or objective-driven reasoning policy, safety cap, roles, skills, or adapters, or needs to repair configuration drift without losing manual edits. Do not select this skill when the request explicitly invokes `$ultracode-help`; `edit` is then only a Help topic.
emanueledenaro/ultracode · ★ 0 · AI & Automation · score 72

Install: claude install-skill emanueledenaro/ultracode

# UltraCode Edit ## Respect explicit Help precedence If the request explicitly invokes `$ultracode-help` or `ultracode-help`, stop before diagnosis or configuration work. Read `../ultracode-help/SKILL.md` and answer `edit` as a read-only Help topic. Change the smallest configuration surface and regenerate only affected managed artifacts. Preserve user-authored content and make drift visible. ## Load and diagnose read-only Read completely: - `../ultracode/references/project-adapter.md` - `../ultracode/references/command-interface.md` - `../ultracode/references/control-and-status.md` - `../ultracode/references/swarm-protocol.md` - `../ultracode/references/reasoning-routing.md` - `../ultracode/references/project-config.schema.json` - `../ultracode/references/managed-manifest.schema.json` Then read `.ultracode/config.json`, `.ultracode/managed.json`, active `AGENTS.md`, and enabled adapter trees. Run the available `project_doctor.py` or `project_doctor.ps1` before editing. If UltraCode is not initialized, route to `$ultracode-init`. Classify the request as config-only, documentation, adapter regeneration, role or skill change, schema migration, or drift repair. Inspect Git status and preserve pre-existing changes. ## Resolve intent and drift When the change is incomplete, ask one to three concise questions. Never ask for an agent count. Allow changes to model policy, objective-driven reasoning defaults and floors, visibility, persistence, approval gates, technical concur