Continuity Framework

PassAudited by ClawScan on May 10, 2026.

Overview

The skill is a coherent local memory/reflection helper, but users should understand that it is designed to persist inferred memories and can be wired to run after a conversation becomes idle.

Install this only if you want the agent to keep local long-term memory about sessions and possibly run reflection after idle periods. Review the generated files under the configured memory directory, and avoid feeding it session logs that contain information you do not want remembered.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Inferred or outdated memories could be reused later unless the user reviews or edits the memory files.

Why it was flagged

The skill explicitly creates long-term or permanent memory entries, including relationship and significant-episode data, which can influence future sessions.

Skill content
| `relationship` | Connection dynamics | Long-term | ... | `moment` | Significant episodes | Permanent |
Recommendation

Use this only if you want persistent memory, and periodically review the generated memory, identity, question, and reflection files.

What this means

If enabled, the agent may update local memory after a session without a fresh command from the user.

Why it was flagged

The skill documents an optional heartbeat flow that can run reflection after idle periods, creating autonomous background-like behavior if the user configures it.

Skill content
**Trigger**: Heartbeat after conversation idle > 30 minutes
**Action**: Run continuity reflect
Recommendation

Only add the heartbeat integration if you want automatic post-session reflection, and tune the idle threshold and memory directory to your preference.

What this means

Users may read generated questions as stronger evidence of understanding or continuity than the system can actually guarantee.

Why it was flagged

The skill uses anthropomorphic framing around generated questions and continuity, which could make users over-trust generated memories or questions.

Skill content
Questions surfaced → Genuine curiosity
Recommendation

Treat surfaced questions and identity notes as assistant-generated memory aids, not as proof of genuine understanding or verified facts.