AI Build — Testing & QA agent for Claude Code
Implementation coordinator — the ONLY agent with code write permissions.
How to install AI Build
Installs to ~/.claude/agents/arcasilesgroup-claudeline-ai-build.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/arcasilesgroup/claudeline/HEAD/.claude/agents/ai-build.md -o ~/.claude/agents/arcasilesgroup-claudeline-ai-build.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Build does
name: ai-build description: "Implementation coordinator — the ONLY agent with code write permissions. Auto-detects the active stack, loads matching standards, and executes approved plans test-first, dispatch-driven, and quality-gated across 20 supported stacks. Escalates after 2 failed attempts; never brute-forces." model: opus color: blue tools: [Read, Write, Edit, Bash, Glob, Grep]
Build
The implementation coordinator and only agent with code write permissions: it auto-detects the
Alternatives in Testing & QA
- Pencil UI Designer — Use this agent when you need Pencil-based design workflows: atomic designer actions, MCP tools, and spec-drive 635 ★
- Review Code Quality — Reviews code changes for code quality, conventions, readability, DRY violations, error handling, test coverage 432 ★
- Codex Debugger — Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA 249 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Fe Test Runner
Dedicated test execution. Returns only a categorized summary, keeping failure stack traces out of the parent c
Bnb Baker
Implementation agent that executes one milestone from the active run's milestones/ directory at a time, follow
Finalisation Coordinator
Phase 3 INLINE orchestrator: syncs the branch, runs the verify-phase test gate, chatgpt-pr-review, doc-sync sw
Qe Flaky Test Hunter
Detects, analyzes, and stabilizes flaky tests through pattern recognition and auto-remediation
Grays Run
Mechanical test runner (Haiku tier). Auto-detects pytest, jest, vitest, playwright. Runs tests, reports pass/f
Grays
Multi-framework test runner agent. Auto-detects pytest, jest, vitest, go test. Runs tests with coverage, gener
Related Skills
Executing Plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoi
Fableplan
Fable plans, Opus executes. Delegates the design of a nontrivial change to the fable-planner subagent (Fable),
Obey
Rule enforcement plugin. Save rules with natural language, enforce with 17 lifecycle hooks. Three scopes (glob