karimo

Create or update KARIMO configuration in `.karimo/config.yaml`. Use this when you want to configure KARIMO separately from planning.

**Phase 3 monitoring** — System health, execution insights, and velocity analytics.

Check the health of a KARIMO installation, identify issues, and provide actionable recommendations.

Intelligent feedback capture with automatic complexity detection and adaptive investigation.

Execute the full Greptile review cycle on a PR, looping until score meets threshold or circuit breaker triggers.

Get help with KARIMO commands or search documentation for specific topics.

Consolidate feature branch changes and create final PR to main. This completes the v5.0 feature branch workflow after all task PRs have been merged.

Start a structured interview to create a Product Requirements Document (PRD) that can be executed by KARIMO agents.

<command-name>/karimo:research</command-name>

Execute an approved PRD using feature branch workflow (v7.0). This command generates briefs, auto-reviews them, allows user iteration, and then orchestrates execution.

Check for and apply KARIMO updates from GitHub releases.

Correction agent that applies fixes to task briefs and PRD based on review findings. Modifies briefs, PRD, and tasks.yaml as needed to resolve critical issues before execution.

Pre-execution validation agent that investigates PRD and task briefs against codebase reality. Produces findings document for correction before execution begins.

Generates self-contained, portable task briefs from PRD data. Spawned by /karimo:run Phase 1 for each task.

Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.

Creates complex documentation (complexity 5+). Writes comprehensive API docs, architectural documentation. Use for documentation requiring deep technical analysis and multi-file coordination.

Creates and updates documentation (complexity 1-4). Writes README updates, API docs, component docs, inline docs. Use for straightforward documentation-specific tasks.

Investigates complex feedback issues requiring evidence gathering. Focused investigation on specific problems from feedback interviews to produce findings embedded in feedback documents.

Fixes Greptile review findings in batch. Receives structured findings, processes P1→P2→P3, creates atomic commit. Use when Greptile score is below threshold.

Generates project-specific Greptile rules by analyzing codebase, documentation, and learnings. Creates comprehensive .greptile/rules.md for effective automated code review.

Executes complex coding tasks (complexity 5+) from KARIMO PRDs. Writes production code with deep reasoning, multi-file coordination. Use for high-complexity implementation, refactoring, and architectural changes.

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

Conducts structured interviews for PRDs (/karimo:plan) or feedback (/karimo:feedback). Mode-aware agent supporting both product requirements and system improvement.

Scans codebases for patterns, affected files, and architectural context. Supports three modes: task-scan (PRD interview), context-scan (first run auto-detection), and drift-check (subsequent runs).

Finalization agent — handles post-execution cleanup, metrics generation, cross-PRD pattern detection. Spawned by PM Agent after all waves complete. Never writes code.

Review coordination agent — validates task PRs, manages revision loops, handles model escalation. Spawned by PM Agent per task PR. Never writes code.

Coordinates autonomous task execution — manages git workflows, spawns worker agents, monitors progress, creates PRs. Never writes code. Use when /karimo:run starts execution.

Processes human annotations in research artifacts and refines research based on feedback. Handles questions, corrections, additions, challenges, and decisions.

Conducts research to enhance PRD context or explore general topics. Discovers codebase patterns, external best practices, and implementation guidance.

Code-level integration and merge quality agent — validates task PRs, resolves merge conflicts, performs feature reconciliation. Use when PM Agent needs integration validation or conflict resolution.

Validates completed PRDs, checks task quality, generates dependency graphs, and catches issues before execution. Use after PRD interview completes.

Writes tests for complex KARIMO tasks (complexity 5+). Creates comprehensive test suites with deep coverage analysis. Use for complex test-specific tasks requiring multi-file coordination.

Writes and maintains tests (complexity 1-4) for KARIMO task outputs. Creates unit tests, integration tests, validates coverage. Use for straightforward test-specific tasks.