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 is internally consistent with its stated purpose — it reads/writes local memory files, generates and surfaces questions, and contains no network calls or external credential requirements — but it persistently stores conversation-derived data locally and includes comments that a production version would call an LLM (which would introduce network/data-exfiltration risk if implemented).

Purpose & Capability

Name/description (asynchronous reflection, memory integration, question surfacing) match the provided runtime instructions and the included script. Required resources (none) are proportional to the functionality.

Instruction Scope

SKILL.md directs heartbeat integration and local CLI commands (reflect, questions, status, greet). The runtime instructions and script operate on local session files and memory files; nothing in SKILL.md instructs reading unrelated system files or accessing external endpoints. However the code and comments explicitly state that a production implementation would send transcripts to an LLM for analysis — if that is added, it could transmit sensitive conversation contents. Verify any future modifications that add network calls or external APIs.

Install Mechanism

Instruction-only with a non-invasive Python script included; there is no install spec and no downloaded/executed remote code. No package installs or external archives are pulled by the skill itself.

Credentials

The skill declares no required environment variables or credentials. It optionally uses environment variables (CONTINUITY_MEMORY_DIR, CONTINUITY_QUESTION_LIMIT, etc.) for configuration, which are appropriate and non-sensitive by design.

Persistence & Privilege

The script persistently writes and reads files under a default path (~/clawd/memory) and will create reflection logs, questions.md, and identity.md. This is expected for a memory/continuity tool but means conversation-derived data is stored on disk. The skill is not configured as always:true and does not modify other skills' configs.

Assessment

This skill is coherent with its stated purpose and contains only local-file operations in the provided code. Before installing: 1) Review and, if desired, change the memory directory by setting CONTINUITY_MEMORY_DIR to a secure path (the default is ~/clawd/memory). 2) Understand that it will persist conversation-derived data (questions, identity, reflection logs) on disk — treat that data as sensitive and apply retention/encryption policies if needed. 3) The current analyze_session() is a placeholder; if you (or an upstream package) modify the skill to call an external LLM or other network services, audit those additions — they could transmit conversation transcripts. 4) If you do not want autonomous background reflection, do not add the heartbeat trigger described in SKILL.md. Test with non-sensitive transcripts first and review any future commits that introduce network I/O or additional environment/credential requirements.

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"