| name | deep-review |
| description | Launch parallel deep-dive agents to review completed work for quality, standards, compatibility, and completeness |
| argument-hint | [feature-name] |
Deep Review
Launch 4 parallel review agents to audit: $ARGUMENTS
Step 0: Identify Target Files
Find all files related to $ARGUMENTS:
Main/Features/$ARGUMENTS/ โ feature code
LOTRAOM.Tests/Features/$ARGUMENTS/ โ tests
Main/Adapters/ โ related adapters
ModuleData/ โ related XML config
docs/ โ feature documentation
Step 1: Launch 4 Parallel Agents (Sonnet)
Agent 1 โ Standards Compliance
Review all target files for:
- ADR-002: Entry points <150 lines, delegate to services
- ADR-003: No
#region blocks
- ADR-004: No
[Obsolete] without full migration in same PR
- ADR-005: No
#if DEBUG except IoC.cs
- ADR-007: Adapter pattern โ no sealed TaleWorlds types in services
- No hardcoded secrets โ IConfiguration for all config values
- Culture lookups โ uses
ICultureMapper.GetLotrCultureName(), never .Name.ToString()
- DryIoC registration โ correct lifetime (Reuse.Singleton vs Transient)
Agent 2 โ Bannerlord Compatibility
- Verify Harmony patch targets exist in the game DLLs
- Check GameModel overrides call
base.Method() for unhandled cases
- Verify method signatures against decompiled source in
External/Decompiled/
- Check for v1.2 โ current API breaking changes
- Verify CampaignBehavior lifecycle hooks are correct
Agent 3 โ Efficiency & Performance
- No unnecessary allocations in hot paths
- String concatenation in loops (use StringBuilder)
- LINQ in performance-critical code
- Correct use of
?. and ?? operators
- Thread safety in shared state
- Dictionary/HashSet vs List for lookups
Agent 4 โ Completeness
- Test coverage โ do tests exist? (80% minimum)
- CHANGELOG updated โ
[Unreleased] section reflects changes
- Documentation โ public APIs have XML doc comments
- ADR created โ if architectural decision was made
- Build passes โ
./build.ps1
- No TODO/FIXME without linked issue
- GitHub issue โ exists for this feature/fix
Step 2: Compile Report
DEEP REVIEW: [target]
=====================
CRITICAL: N findings
HIGH: N findings
MEDIUM: N findings
LOW: N findings
[Grouped findings by agent, with file:line references]
VERDICT: CLEAN / NEEDS FIXES / BLOCKED