haterade22

Root-cause native Bannerlord CTDs (AccessViolation in TaleWorlds.Native.dll) via Event Log offsets, offline disassembly, and live debugger forensics. No symbols needed.

Dispatch an independent Codex verification job directly via `codex exec` Bash call, then retrieve and present results

Inspect all changed files, group by logical concern, and guide atomic per-concern commits following TAOM's 50/72 rule and commit trailer convention.

Load a snapshot saved by /context-save and present it so this session can pick up where the last one left off without re-deriving decisions.

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

Respond to a Bannerlord engine update (Steam force-bump or deliberate migration) — preserve the decompile baseline, regen, diff, re-verify bindings and creature data, control-battle.

Integrate a merge-ready branch into the trunk — fast-forward check, merge, regenerate backlinks, CHANGELOG, delete branch (local+remote), push with confirmation. TAOM trunk-based, not Git Flow.

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.

Author a culture's armor items and swap troop equipment rosters via the generator + validation pipeline. Use when adding/revamping armor. Enforces the canonical-folder + cover-attribute rules.

Give DOTS lords lore-driven skill values and traits via the DOTS SkillSet system. Use when a canonical lord has wrong stats or a culture roster needs a balance pass.

Author or revamp a DOTS culture's armor set, troop tree, and recruitment wiring end-to-end. Use for new cultures or troop-tree revamps. Follows docs/ai-includes/new-culture-authoring.md.

Use when reviewing an external repo or article to adopt practices into DOTS — security-vet first, map novel vs duplicative, port (never install), review, commit your changes.

Structured 4-phase self-debug for failing agent runs (looping, drifting, burning tokens). Capture, diagnose, contained recovery, report. Complements /investigate (which is for code bugs); this skill is for harness/agent failures.

Incrementally fix dotnet build errors with minimal diffs, one error at a time

Dispatch an independent Codex verification job directly via `codex exec` Bash call, then retrieve and present results

Inspect all changed files, group by logical concern, and guide atomic per-concern commits following DOTS's 50/72 rule and commit trailer convention.

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

Incrementally fix build errors with minimal diffs, one error at a time

Dispatch an independent Codex verification job for the current changes

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

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

Regression-safe cleanup of AI-generated bloat in Lua code. Deletion-first, requires passing tests before starting

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

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

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