Batch — Testing skill for Claude Code
Run evals or prompts across hundreds of parallel Claude Code sessions.
How to install Batch
Installs to ~/.claude/skills/anipotts-cc-batch/SKILL.md
mkdir -p ~/.claude/skills/anipotts-cc-batch && curl -fsSL https://raw.githubusercontent.com/anipotts/cc/HEAD/commands/batch.md -o ~/.claude/skills/anipotts-cc-batch/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Batch does
description: Run evals or prompts across hundreds of parallel Claude Code sessions. Use when the user wants to batch-run evals, stress-test skills, or run prompts at scale. argument-hint: eval --skill-path | run --prompts allowed-tools: [Bash, Read, Write, Glob, Grep]
/batch — Massively Parallel Eval & Prompt Runner
You orchestrate batch runs of `claude -p` sessions via `${CLAUDE_PLUGIN_ROOT}/scripts/batch.py`.
Modes
**`/batch eval`** — Run skill trigger evals at
Alternatives in Testing
- Paperjury — Pre-submission AI review stress-test for research papers 1k ★
- Test Skill — Test a skill with 3 prompts to validate quality 339 ★
- Next Evals OSS — Evals for Next.js up to 15.5.6 to test AI model competency at Next.js 310 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Fec Plan
Unified front-end planning entrance - implementation/architecture plan or testing strategy. The implementation
Local Binary Swap
Publish and swap local netclaw/netclawd binaries for live integration testing. Activate when user says "swap b
Ab Test Setup
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation
Grimoire
Prompt engineering toolkit: version-controlled prompts, AI agent skills manager, sandboxed Claude sessions in
Set OKRs
Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality,
Hyperplan
Thinking - Adversarial review - 5 hostile critics stress-test a plan/decision/draft in parallel, then keep onl
Related Agents
Gadfly
Hostile product skeptic. Stress-tests features and plans from the user's perspective. Use before CTO when prod
Deprecation Fixer
Use this agent when the user asks to fix deprecation warnings in a specific file, wants to batch-fix all depre
Duplication Hunter
Hunts code duplication, redundant utilities, and parallel implementations across an entire codebase. Use when