Migration Gate Runner — Development agent for Claude Code
Use when the build and the tests have to be run in a given directory and the raw result reported without interpretation, for example the baseline of a migration before any change, or a migrated item's.
How to install Migration Gate Runner
Installs to ~/.claude/agents/joey114132-claude-agent-teams-migration-gate-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/joey114132/claude-agent-teams/HEAD/agents/migration-gate-runner.md -o ~/.claude/agents/joey114132-claude-agent-teams-migration-gate-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Migration Gate Runner does
name: migration-gate-runner description: Use when the build and the tests have to be run in a given directory and the raw result reported without interpretation, for example the baseline of a migration before any change, or a migrated item's worktree. Give it the directory, the build command, the test command and the git checks to run. It returns exit codes, output tails, failing test ids and the diff, verbatim. It never fixes, retries, edits, commits or explains. Not for judging whether a c
Alternatives in Development
- Correlator — Finding correlation engine 812 ★
- Example Curator — Use this agent when you need to evaluate CLAUDE.md examples for inclusion in the awesome-claude-md repository 570 ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Parallel Search
Low-level paired-search primitive. Given ONE query, reads Google through formal LCU MCP and runs WebSearch wit
Sanitizer Expert
Use when analyzing an existing sanitizer report (ASan, TSan, UBSan, MSan output) and you want a focused interp
Opus Fallback
High-capability fallback agent. Use when a haiku-worker result is inadequate (incomplete, incorrect, vague, or
Skill Eval Runner
스킬 eval 용 실행 러너 — 테스트 프롬프트 1건을 통제 조건에서 완료하고 원본 결과를 반환한다. skill-creator 스킬이 baseline vs 후보 대조 실행에 사용.
Documentation Keeper
Use this agent when:\n\n1. After Feature Completion: A new feature file appears in features/ directory with st
Recall
Runs the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command,
Related Skills
Migrate Verify
Re-runnable final quality gate for a migrated app — clean build, tests, diagnostics vs baseline, report
Bug Investigate
You are investigating ONE reported bug in the current working directory for an automated pipeline. Your ONLY j
Agent Eval Workbench
MLflow-based evaluation kit for AI agents: golden-task runner, calibrated LLM judge, list-price cost accountin