Reset
Archive an in-progress FPF reasoning session and clear active hypothesis work so the agent can start a fresh cycle without losing history.
Overview
Reset is an agent skill most often used in Build (also Idea, Validate) that archives the current FPF session and clears active hypothesis work so you can start a fresh reasoning cycle.
Install
npx skills add https://github.com/neolabhq/context-engineering-kit --skill resetWhat is this skill?
- Soft reset archives the current FPF session to .fpf/sessions/ with reason and timestamp metadata
- Optional move of active L0/L1/L2 markdown hypotheses into .fpf/archive/ for a clean slate
- Captures hypothesis counts by level and whether a decision was finalized at reset time
- Reports reset completion paths so the user knows what was preserved versus cleared
- Supports user-requested fresh starts without silently deleting prior reasoning artifacts
- Soft reset writes session metadata plus optional L0/L1/L2 file archive
Adoption & trust: 511 installs on skills.sh; 1.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your FPF or context-engineering session is cluttered with abandoned hypotheses and you need a fresh cycle without losing what was tried.
Who is it for?
Builders using neolab context-engineering-kit FPF layouts who switch problems mid-session or need a documented abandon-and-restart.
Skip if: Projects not using .fpf knowledge directories or anyone who needs to delete git history instead of archiving agent reasoning state.
When should I use this skill?
User requests a fresh FPF start or the reasoning cycle should be archived before beginning new hypotheses.
What do I get? / Deliverables
After reset, the prior session is archived under .fpf/sessions/ with optional knowledge files moved to archive, leaving active directories clear for a new cycle.
- Session archive markdown in .fpf/sessions/
- User-facing reset summary listing archived files and hypothesis counts
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build/agent-tooling is where structured agent knowledge directories and reasoning kits live; reset is the operational control for that workspace. Agent-tooling captures session lifecycle management—archiving L0/L1/L2 state—not application feature code.
Where it fits
Archive a stuck L1 verification thread and empty active L0/L1 folders before invoking the next FPF skill.
Reset after competitive research hypotheses were rejected so new L0 proposals do not mix with old notes.
Pivot product scope and soft-reset so prior unvalidated hypotheses are archived but traceable.
How it compares
Use instead of manually deleting markdown hypotheses without a session record or conflating reset with reverting application code.
Common Questions / FAQ
Who is reset for?
Reset is for developers running FPF-style agent reasoning with .fpf knowledge folders who need a controlled fresh start.
When should I use reset?
Use it in Build agent-tooling when abandoning a hypothesis branch, after Validate scope pivots, or in Idea research when you want a clean L0 slate with prior work archived.
Is reset safe to install?
Review the Security Audits panel on this Prism page; reset can move or archive files under .fpf, so confirm paths and backups before granting shell and filesystem access.
SKILL.md
READMESKILL.md - Reset
# 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: 1. **Create Session Archive** Create a file in `.fpf/sessions/` to record the completed/abandoned session: ```markdown # 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. ``` 2. **Move Active Work to Archive** (Optional) If user wants to clear the knowledge directories: ```bash mkdir -p .fpf/archive/session-2025-01-15 mv .fpf/knowledge/L0/*.md .fpf/archive/session-2025-01-15/ 2>/dev/null || true mv .fpf/knowledge/L1/*.md .fpf/archive/session-2025-01-15/ 2>/dev/null || true mv .fpf/knowledge/L2/*.md .fpf/archive/session-2025-01-15/ 2>/dev/null || true ``` 3. **Report to User** ```markdown ## Reset Complete Session archived to: .fpf/sessions/session-2025-01-15-reset.md Current state: - L0: 0 hypotheses - L1: 0 hypotheses - L2: 0 hypotheses Ready for new reasoning cycle. Run `/fpf:propose-hypotheses` to start. ``` ### Option 2: Hard Reset (Delete All) **WARNING**: This permanently deletes all FPF data. ```bash rm -rf .fpf/knowledge/L0/*.md rm -rf .fpf/knowledge/L1/*.md rm -rf .fpf/knowledge/L2/*.md rm -rf .fpf/knowledge/invalid/*.md rm -rf .fpf/evidence/*.md rm -rf .fpf/decisions/*.md ``` Only do this if explicitly requested by user. ### Option 3: Decision Reset (Keep Knowledge) If user wants to re-evaluate existing hypotheses: 1. Move L2 hypotheses back to L1 (re-audit) 2. Or move L1 hypotheses back to L0 (re-verify) ```bash # Re-audit: L2 -> L1 mv .fpf/knowledge/L2/*.md .fpf/knowledge/L1/ # Re-verify: L1 -> L0 mv .fpf/knowledge/L1/*.md .fpf/knowledge/L0/ ```