From episteme
Designs safe unattended or long-running loops with explicit limits, checkpoints, and handoff artifacts for automation beyond one interactive session.
How this skill is triggered — by the user, by Claude, or both
Slash command
/episteme:bounded-loop-runnerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when a user wants automation beyond one interactive session.
Use this skill when a user wants automation beyond one interactive session.
Include:
Do not default to unattended code-writing loops without explicit safeguards.
npx claudepluginhub junjslee/episteme --plugin epistemeRuns tasks in a loop until a goal is met, with configurable success criteria, max iterations, and progress tracking. Useful for iterative refinement, polling, or convergence workflows.
Executes tasks iteratively until completion with structured completion signals, stagnation detection, and dual-condition exit gates. Useful for autonomous multi-step workflows.
Re-enters long-running Plans.md execution with fresh context using /loop dynamic mode and ScheduleWakeup. Invokes harness-work per cycle. Useful for autonomous multi-cycle task execution with configurable pacing.