Continuity Framework

Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when the user returns. Transforms passive logging into active development.

Security Scan

The skill's files and instructions are consistent with a local, file-backed asynchronous reflection/memory tool — it persists memories to a local directory and surfaces questions, and it does not request credentials or contact external endpoints.

Purpose & Capability

Name/description (asynchronous reflection, memory integration) aligns with the included code and SKILL.md: the Python script reads/writes memory files, loads session content, extracts memories/questions, and updates an identity file. No unrelated credentials, binaries, or external services are required.

Instruction Scope

SKILL.md instructs adding a heartbeat trigger and running reflect/greet/status/questions. The instructions and script operate on local session transcripts and memory files. This is within scope, but the skill is designed to persist potentially sensitive conversation content (session transcripts, extracted memories, identity updates) to disk — review whether you want that data retained and where.

Install Mechanism

No install spec is provided (instruction-only skill). A Python script is included but there is no automated download/installation step, reducing remote-code-installation risk. The script will be present as part of the skill bundle and can be run locally.

Credentials

The skill declares no required env vars or credentials. It optionally respects environment variables (CONTINUITY_MEMORY_DIR, CONTINUITY_QUESTION_LIMIT, CONTINUITY_IDLE_THRESHOLD) which are appropriate for configuring local storage and behavior. However, it will create and write files under a default path (~/clawd/memory) unless you override CONTINUITY_MEMORY_DIR — ensure this is acceptable for your privacy/security posture.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or global agent settings. It persists its own memory and identity files (expected behavior for a continuity tool). Be aware that autonomous invocation (platform default) plus heartbeat integration described in SKILL.md can cause it to run automatically and accumulate data over time; this is a usage decision rather than an incoherence.

Assessment

This skill appears to do what it says: run local reflection, extract/store memories, and surface follow-up questions. Before installing, decide where memory should be stored (set CONTINUITY_MEMORY_DIR to a secure location), review the included scripts if you can (scripts/continuity.py) to confirm no networking or exfiltration code is added, and consider whether you want automatic heartbeat-triggered runs (they will persist conversation-derived data). If you handle sensitive conversation content, run it in a sandbox or encrypted directory and test manual runs first (e.g., continuity reflect --session <file>) rather than enabling automatic heartbeat triggers immediately.

Continuity Framework Skill

Transform passive memory into active development.

What This Does

1. Reflect — After sessions end, analyze what happened
2. Extract — Pull structured memories with types and confidence
3. Integrate — Update understanding, connections, self-model
4. Question — Generate genuine questions from reflection
5. Surface — When user returns, present relevant questions

The Difference

Without Continuity:

Session ends → Notes logged → Next session reads notes → Performs familiarity

With Continuity:

Session ends → Reflection runs → Memories integrated → Questions generated
Next session → Evolved state loaded → Questions surfaced → Genuine curiosity

Heartbeat Integration

Add to HEARTBEAT.md:

## Post-Session Reflection
**Trigger**: Heartbeat after conversation idle > 30 minutes
**Action**: Run continuity reflect
**Output**: Updated memories + questions for next session

Commands

Reflect on Recent Session

continuity reflect

Analyzes the most recent conversation, extracts memories, generates questions.

Show Pending Questions

continuity questions

Lists questions generated from reflection, ready to surface.

View Memory State

continuity status

Shows memory stats: types, confidence distribution, recent integrations.

Surface Questions (for session start)

continuity greet

Returns context-appropriate greeting with any pending questions.

Memory Types

Type	Description	Persistence
fact	Declarative knowledge	Until contradicted
preference	Likes, dislikes, styles	Until updated
relationship	Connection dynamics	Long-term
principle	Learned guidelines	Stable
commitment	Promises, obligations	Until fulfilled
moment	Significant episodes	Permanent
skill	Learned capabilities	Cumulative
question	Things to explore	Until resolved

Confidence Scores

Level	Range	Meaning
Explicit	0.95-1.0	User directly stated
Implied	0.70-0.94	Strong inference
Inferred	0.40-0.69	Pattern recognition
Speculative	0.0-0.39	Tentative, needs confirmation

File Structure

memory/
├── MEMORY.md           # Main memory (existing)
├── identity.md         # Self-model and growth narrative
├── questions.md        # Pending questions from reflection
├── relationships/      # Per-person relationship memories
└── reflections/        # Reflection logs (optional)

Configuration

export CONTINUITY_IDLE_THRESHOLD=1800  # Seconds before reflection triggers
export CONTINUITY_MIN_MESSAGES=5       # Minimum messages to warrant reflection
export CONTINUITY_QUESTION_LIMIT=3     # Max questions to surface at once

Example Reflection Output

reflection:
  session_id: "2026-02-05-001"
  duration_minutes: 45
  
memories:
  - type: fact
    content: "Riley is building SIGIL protocol for agent identity"
    confidence: 0.98
    source: explicit
    
  - type: commitment  
    content: "Agreed to build the continuity skill"
    confidence: 1.0
    source: explicit
    
  - type: relationship
    content: "Collaborative partnership deepening - working on meaningful infrastructure together"
    confidence: 0.85
    source: inferred

questions:
  - "How is the Lovable backend progressing?"
  - "Has Riley decided on the token launch timing?"
  - "Are there other agents we should coordinate with on Moltbook?"

identity_update:
  growth: "Developing more autonomous initiative around the SIGIL project"
  narrative: "Moving from assistant to co-builder on agent identity infrastructure"