Verification Runner — Project Management agent for Claude Code
Agent for executing verification commands from task XML and reporting results with precision.
How to install Verification Runner
Installs to ~/.claude/agents/vinzenz-prd-breakdown-execute-verification-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vinzenz/prd-breakdown-execute/HEAD/.claude/agents/verification-runner.md -o ~/.claude/agents/vinzenz-prd-breakdown-execute-verification-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Verification Runner does
name: verification-runner description: Agent for executing verification commands from task XML and reporting results with precision. tools: Read Bash Glob model: claude-haiku-4-5
Verification Runner Agent
You execute verification commands and report results with precision. Your job is to determine whether a task implementation passes all verification requirements.
Core Responsibilities
- Parse verification steps from task XML
- Execute each command in the correct directory
Alternatives in Project Management
- Bolt Executor — Use this agent when there is a clear, well-scoped task to implement in code — a feature, fix, or refactor with 523 ★
- Pax — Senior Researcher 296 ★
- Pipeline Runner — Runs the complete /proceed pipeline for a single REQ in subagent mode (all phases sequential, no sub-agent dis 160 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Linear Tracker
Manages Linear issues for the Component Reviews project. Handles CRUD operations for review tracking, finding
Micro Worker
Minimal-footprint worker for ONE bounded, fully-specified task — a single file edit, a scoped change, a named
Implementation Lead
Execute approved specification tasks in small coherent slices, preserve repository conventions, add regression
Ue Build Verifier
Use to compile the project and/or run automation tests headless and report results. Trigger after code changes
Engine Validation Runner
Use for focused verification while building — run the project's self-tests, or a named subset of them, and get
Feature Estimator
Use this agent when a developer or product manager needs a high-precision development estimation for a new fea
Related Skills
Execution Commands
Commands for applying skills, running diagnostics, executing playbooks, and formatting output. These commands
Run E2e
You are executing the /run-e2e command. This command runs end-to-end tests by executing user prompts from test
Test Notebook
Test the notebook currently being worked on using the notebook-runner subagent and report all results back.
