From episteme
Designs safe unattended or long-running loops with explicit limits, checkpoints, and handoff artifacts for automation beyond single sessions.
npx claudepluginhub junjslee/episteme --plugin epistemeThis skill uses the workspace's default tool permissions.
Use this skill when a user wants automation beyond one interactive session.
Executes tasks in structured loops until goals met, with max iterations, success evaluations, progress tracking, and safety checks for refinement or convergence.
Enables autonomous loop mode for any project via interactive setup of priorities for bug fixes, features, performance, refactoring, security, tests, and more.
Restructures human-in-the-loop workflows into autonomous LLM CLI loops with file outputs, structured logs, and trap-or-abandon decisions. For iterative grunt work, web UIs, dashboards, or Claude automation.
Share bugs, ideas, or general feedback.
Use this skill when a user wants automation beyond one interactive session.
Include:
Do not default to unattended code-writing loops without explicit safeguards.