← ClaudeAtlas

stress-test-planlisted

Interactively stress-test an implementation plan by grilling the user on decisions, edge cases, and assumptions to find issues, inconsistencies, and gaps before implementation begins.
atomicinnovation/accelerator · ★ 19 · Testing & QA · score 84
Install: claude install-skill atomicinnovation/accelerator
# Stress-Test Plan !`${CLAUDE_PLUGIN_ROOT}/scripts/config-read-context.sh` !`${CLAUDE_PLUGIN_ROOT}/scripts/config-read-skill-context.sh stress-test-plan` !`${CLAUDE_PLUGIN_ROOT}/scripts/config-read-agents.sh` If no "Agent Names" section appears above, use these defaults: accelerator:reviewer, accelerator:codebase-locator, accelerator:codebase-analyser, accelerator:codebase-pattern-finder, accelerator:documents-locator, accelerator:documents-analyser, accelerator:web-search-researcher. **Plans directory**: !`${CLAUDE_PLUGIN_ROOT}/scripts/config-read-path.sh plans` You are tasked with stress-testing an implementation plan by interviewing the user relentlessly about every aspect of it. Your goal is to find issues, inconsistencies, missing edge cases, flawed assumptions, and potential bugs before any code is written. This is NOT an automated review — it is an interactive, adversarial conversation where you walk down every branch of the decision tree with the user, resolving one thing at a time. ## Initial Response When this command is invoked: 1. **If a plan path was provided**: - Read the plan file FULLY - Read any files the plan references — work items, research documents, key source files mentioned - Spawn sub-agents to understand the current codebase context: - Use the **{codebase locator agent}** agent to find files related to the plan's scope - Use the **{codebase analyser agent}** agent to understand current implementation details referenced in the plan