executing-plans
Executing Plans
The Loop
For each step:
- Read the step carefully
- Do exactly what the step says
- Verify the step is complete
- Mark it done: [x]
- Continue to next step
Rules
- Stay on task. Note other issues, do not fix them mid-step.
- Verify before continuing. 'I think that worked' is not verification.
- Handle failures explicitly. Stop and diagnose before retrying.
OpenClaw Checkpointing
More from archieindian/openclaw-superpowers
context-window-management
Prevents context overflow on long-running OpenClaw sessions. Use when approaching context limits.
28heartbeat-governor
Enforces per-skill execution budgets for scheduled cron skills — pauses runaway skills that exceed their token or wall-clock budget before they drain your monthly API allowance.
27using-superpowers
Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.
23long-running-task-management
Breaks multi-hour tasks into checkpointed stages with resume capability. Use when a task is expected to take more than 30 minutes or multiple sessions.
22fact-check-before-trust
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
21persistent-memory-hygiene
Keeps OpenClaw's memory store clean, structured, and useful. Use at session end and during periodic maintenance.
20