zenflow

Audit codebase against code standards. Pass "changed" for diff-only mode.

Diagnose and fix a bug with parallel diagnostic agents

Run all quality gates — lint, format, tests, docs, journal

Shed context mid-session with a knowledge handoff document for clean resumption after /clear.

Execute a plan with parallel subagents per task

Fresh specialist agent spawned by zenflow:collab to handle issues extracted from the primary working session. Receives a structured handoff with full context, fixes the issue independently and reports back.

Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across multi-agent systems with focus on minimizing impact and learning from failures.

Expert error detective specializing in complex error pattern analysis, correlation, and root cause discovery. Masters distributed system debugging, error tracking, and anomaly detection with focus on finding hidden connections and preventing error cascades.

Audit codebase sections against configurable code standards using parallel specialist agents. Use when checking code quality, enforcing standards, or running periodic health checks on the codebase.

Use when fixing bugs, errors, or unexpected behavior. Launches parallel diagnostic agents then a specialist to fix. Use for any issue that starts with "X is broken", "X doesn't work", error reports, or failing tests.

Validate completed work passes all quality gates (lint, format, tests, docs, journal). Use after finishing implementation tasks to ensure nothing is missed. Fixes failures automatically using subagents.

Collaborative working session — you and the user are a team exploring, building, and troubleshooting together. When issues arise, extract them with full context and delegate to fresh agents so the primary session stays clean and productive.

Shed accumulated context mid-session. Writes a knowledge handoff document capturing session state, decisions, observations, and behavioral calibration, then guides the user through /clear and resumption.