Clears out your FPF reasoning cycle when you need to start over. Gives you three options: soft reset archives the current session to a timestamped file and optionally moves hypotheses to an archive folder, hard reset nukes everything (use carefully), or decision reset moves validated hypotheses back down a level for re-evaluation. The soft reset is smart about preserving state, creating a session record with counts of what you had at each level and why you stopped. Honestly most useful when a reasoning thread has gone sideways and you'd rather begin fresh than try to salvage it, though the archive means you can always look back if needed.
- skills.sh installs
- 1.2K
- GitHub stars
- 1.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add neolabhq/context-engineering-kit --skill reset --agent claude-codeInstalls into .claude/skills of the current project.
Files
Reset Cycle
Reset the FPF reasoning cycle to start fresh.
Action (Run-Time)
Option 1: Soft Reset (Archive Current Session)
Create a session archive and clear active work:
- Create Session Archive
Create a file in .fpf/sessions/ to record the completed/abandoned session:
# In .fpf/sessions/session-2025-01-15-reset.md
---
id: session-2025-01-15-reset
action: reset
created: 2025-01-15T16:00:00Z
reason: user_requested
---
# Session Archive: 2025-01-15
**Reset Reason**: User requested fresh start
## State at Reset
### Hypotheses
- L0: 2 (proposed)
- L1: 1 (verified)
- L2: 0 (validated)
- Invalid: 1 (rejected)
### Files Archived
- .fpf/knowledge/L0/hypothesis-a.md
- .fpf/knowledge/L0/hypothesis-b.md
- .fpf/knowledge/L1/hypothesis-c.md
### Decision Status
No decision was finalized.
## Notes
Session ended without decision. Hypotheses preserved for potential future reference.
- Move Active Work to Archive (Optional)
If user wants to clear the knowledge directories:
Sponsors
Details
- Repository
- github.com/neolabhq/context-engineering-kit
- First seen
- Jun 3, 2026
More from neolabhq/context-engineering-kit
All 63- Setup Context7 Mcp1.2K
- Prompt Engineering1.5K
- Context Engineering1.5K
- Thought Based Reasoning1.4K
- Reflect1.4K
- Write Concisely1.4K
- Kaizen1.4K
- Multi Agent Patterns1.4K
- Memorize1.3K
- Update Docs1.3K
- Critique1.3K
- Brainstorm1.3K
- Judge With Debate1.3K
- Root Cause Tracing1.3K
- Agent Evaluation1.3K
- Subagent Driven Development1.3K
- Review Local Changes1.3K
- Test Driven Development1.3K
- Plan Task1.3K
- Judge1.3K
- Why1.3K
- Do And Judge1.3K
- Setup Serena Mcp1.3K
- Implement Task1.3K
