LOTRAOM

Audit context window consumption across LOTRAOM agents, skills, rules, MCP servers, and CLAUDE.md. Report token estimates, flag bloat, recommend trims.

Hard-block Edit/Write outside a chosen directory. Use to scope-lock edits during a focused fix or refactor. Pair with /unfreeze to release.

Six-phase root-cause debugging for crashes, build failures, or "why is this broken" reports. Iron Law - no fixes without root cause. Auto-engages /freeze.

Release the directory edit lock set by /freeze. Edit and Write are unrestricted again. No-op if /freeze was never set.

Dispatch an independent Codex verification job for the current changes

Inspect all changed files, group by logical concern, and guide atomic per-concern commits

Check mod compatibility against a new Bannerlord version by reviewing patch targets and GameModel overrides

Launch parallel deep-dive agents to review completed work for quality, standards, compatibility, and completeness

Regression-safe cleanup of AI-generated bloat in C# code. Deletion-first, requires green tests

Create a GitHub issue with structured sections for a feature, bug fix, or crash

Scaffold a new Architecture Decision Record, auto-numbered from existing ADRs

Decompile and analyze TaleWorlds classes before implementing or fixing

Auto-detect what was built, write a Codex adversarial prompt, dispatch, then verify results

Assess whether a proposed change fits the current work context or represents scope creep

Review last 2 weeks of Claude Code and VS Code updates, cross-reference against project config to find improvements