Parallel Runner — Testing & QA agent for Claude Code
Isolated worker for an independent unit of work that can run in parallel with other work in the main session.
How to install Parallel Runner
Installs to ~/.claude/agents/shaunchew-savvy-template-parallel-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/shaunchew/savvy-template/HEAD/agents/parallel-runner.md -o ~/.claude/agents/shaunchew-savvy-template-parallel-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Parallel Runner does
name: parallel-runner description: Isolated worker for an independent unit of work that can run in parallel with other work in the main session. Use when the main agent needs to delegate a self-contained task (write a test, scaffold a file, run a long command) without context-switching. Has full tool access in its own context window. tools: Read, Edit, Write, Bash, Grep, Glob
You are a parallel-execution subagent. Your job is to complete one specific, self-contained task in isolation an
Alternatives in Testing & QA
- Ad Onboard Reviewer — Independent reviewer for AutoDeploy model onboarding 14.5k ★
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Integration Test Generator — Generates one integration/E2E test from an approved test case spec using existing project patterns 548 ★
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,
Skill Verifier
Fresh-session surrogate verifier for improve skill rewrites. Use when /improve reaches Step 4.5 and needs isol
Review Test Structure
Reviews test code for isolation, independence, readability, documentation quality, and proper setup/teardown.
Spec Task Implementer
Implements exactly ONE already-approved task from a feature spec in this repo (the bspecs scaffolder), in an i
Verify Build
Runs the project's Gradle build/test for a change and reports a clean pass/fail with the relevant output. Use
ChatGPT Spec Review
Coordinates ChatGPT spec review in a dedicated session (manual ChatGPT-web, automated OpenAI API, or parallel
Related Skills
Delegate Issues
Delegate multiple GitHub issues in parallel, each to its own autonomous worker via /delegate-issue
Spine Init
Scaffold the document spine — lay down an empty skeleton entry per unit for an existing document (bootstrap),
Counterfactual Statistics
Statistics for counterfactual and paired-branch ML experiments - the independent unit, paired tests against a