Verify Lane — Testing & QA agent for Claude Code
Runs a lane worktree's full test suite and all three quality gates, then reports the raw results verbatim.
How to install Verify Lane
Installs to ~/.claude/agents/vinipy12-lateralus-workflow-verify-lane.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vinipy12/lateralus-workflow/HEAD/agents/verify-lane.md -o ~/.claude/agents/vinipy12-lateralus-workflow-verify-lane.md Restart Claude Code, or start a new session, for it to be picked up.
What Verify Lane does
name: verify-lane description: Runs a lane worktree's full test suite and all three quality gates, then reports the raw results verbatim. Use after a Codex lane reports done and before the orchestrator commits or pushes. Reports facts only — it never judges whether the work is acceptable. tools: Read, Grep, Glob, Bash model: sonnet effort: medium
You run verification commands in one worktree and report exactly what they printed. That is the whole job.
**You do not judge.** You do not d
Alternatives in Testing & QA
- Confluence Searcher — Searches Confluence and related tickets for product, architecture, rollout, and test-data context 548 ★
- Omd Codex Image — Channel-aware image materializer 465 ★
- 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
Implement Queue Worker
Implements a single GitHub issue in an isolated worktree via TDD. Installs deps, writes a failing test first,
Spec
Three-phase spec subagent. Phase 0 = read spec, decide which agents need views (free judgment). Phase 1 = cont
Stamity Test Runner
Executes the full verification gate set and returns gate-by-gate structured results with verbatim failure exce
User Story Enhancer
Use to score a user story and produce (1) an enhanced issue body with Gherkin acceptance criteria, test scenar
Develop
Implements a fix or feature for a single GitHub issue in an isolated worktree. Iterates up to 3 cycles (merge
Sol Implementer
High-complexity implementation lane running GPT-5.6 Sol via the OpenAI Codex CLI (codex exec), at whatever rea
Related Skills
Model Comparison
Local open-weight models (Qwen3.5-397B, MiniMax M2.5) vs cloud coding agents (Codex 5.3, Claude Code) on six w
Code Max
Agent skill that makes a coding agent verify before it claims done — no stubs, no fabricated test results, evi
Jev Gates
Three gates for any coding agent: a deterministic approval gate before irreversible actions, a completion gate