aa-ma-forge

Use multiple Claude agents to investigate and fix independent problems concurrently

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.

Synthesize a Claude Code /goal condition from AA-MA plan artifacts. Produces a falsifiable condition referencing observable artifacts (provenance.log, tasks.md, git tags, test exit codes) plus a turn cap derived from plan effort. Owns the canonical verdict-token enum, observable-artifact list, hashing contract, and turn-cap formula. Used by /execute-aa-ma-full §2.5 and /verify-plan --iterate.

Use when executing tasks from AA-MA artifacts - handles step/milestone/full execution with proper context injection, validation, and provenance logging. Proactively use when detecting .claude/dev/active/ directories or when user asks to continue/resume work.

Use when planning complex multi-step tasks, creating AA-MA artifacts, or transitioning from ad-hoc to structured development - transforms rough ideas into executable plans through 5-phase workflow with integrated skills and validation gates

Post-impl adversarial review symmetric to /verify-plan. Dispatches up to 5 parallel audit agents (code-reviewer, security-auditor, tdd-sequence-auditor, context7-evidence-auditor, future-proofing-auditor) based on the milestone's plan-declared Audit-Profile. CRITICAL findings surface via AskUserQuestion accept/dispute/defer panel before §7.3 user authorization. Introduced in v0.8.0 per ADR-0005. Invoked by Phase 6.8 of /execute-aa-ma-milestone.

Adversarial verification of AA-MA plans using 6 independent angles. Catches factual errors, unverified assumptions, impact gaps, vague criteria, implementation barriers, and domain-specific risks before plans reach execution. Invoked by Phase 4.5 of aa-ma-plan and standalone /verify-plan command.

Activate comprehensive operational constraints for disciplined execution. Use at session start, before complex tasks, during planning phases, or when encountering friction. Enforces token efficiency, tool protocols, parallel execution, TDD, and system mapping.

Output token compression for AA-MA workflows. Reduces response tokens by 40-75% while preserving full technical accuracy. Three intensity levels mapped to execution modes: lite (HITL), full (general), ultra (AFK). Auto-activates during AA-MA execution based on task Mode field. Manual activation via /compress lite|full|ultra.

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

Estimate task complexity and route high-complexity tasks (>=80%) to deep architectural review - use before plan generation

Orchestrate Claude Code agent teams for collaborative multi-agent work. Use when tasks need 2+ coordinated agents that communicate with each other. Supports research teams (competing hypotheses, parallel investigation), implementation teams (architect + implementers + reviewer), hybrid teams, and code review teams. Integrates with AA-MA for structured execution. Handles team creation, task distribution, inter-agent debate, progress monitoring, error recovery, and graceful shutdown. Keywords: team, teammate, multi-agent, swarm, coordinate, collaborate, spawn agents, parallel agents communicate, competing hypotheses, research team, implementation team.

Enforce dependency awareness before code edits. Use when modifying existing code, changing function signatures, working on AA-MA milestones, or editing shared/core modules. Prevents breaking changes by analyzing upstream callers, downstream dependencies, and contract changes.

Lightweight pre-flight checklist for understanding system context before code changes. Perform 5-point analysis of architecture, execution flows, logging, dependencies, and environment. Use before modifying unfamiliar code or multi-file changes.