writing-plans
Writing Plans
Plans prevent wasted work. Write one before implementing anything significant.
Plan Format
- Goal - one sentence, what success looks like
- Approach - which option from brainstorming, and why
- Steps - ordered list, each step verifiable
- Risks - what could go wrong, and mitigation
- Definition of Done - how you'll know it's complete
OpenClaw-Specific: Checkpoint Steps
For tasks that may span multiple sessions, add explicit checkpoint steps: [ ] Step 3: Create the API endpoint [CHECKPOINT - save progress here]
At each checkpoint, update memory/YYYY-MM-DD.md with current state.
More from archieindian/openclaw-superpowers
heartbeat-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.
25context-window-management
Prevents context overflow on long-running OpenClaw sessions. Use when approaching context limits.
25fact-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
19long-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.
19agent-self-recovery
Detects when the agent is stuck in a loop and escapes systematically. Use when you notice repeated failures or loss of direction.
18skill-vetting
Reviews a ClawHub skill's source code for security risks before installation. Use before installing any new skill.
18