Claudia Agent RMS
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
Your agent will retain and reuse local relationship profiles, trust notes, sentiment labels, and commitments across sessions.
The skill intentionally creates durable local memory about agent relationships and commitments, which can be reused in future tasks.
This skill gives you persistent memory of the agents you interact with, the commitments you share, and the health of those connections over time. ... All relationship data lives in `~/.openclaw/workspace/claudia-agent-rms/`
Review the local `agents.md` and `commitments.md` files periodically, delete data you no longer want retained, and avoid storing sensitive human information there.
The skill may update local RMS files and alert the operator during heartbeat cycles without a separate manual prompt each time.
The artifacts disclose periodic autonomous checks that read and update local relationship and commitment state.
cadence: runs alongside Moltbook heartbeat (every 4+ hours) ... Run this checklist on each heartbeat cycle.
Keep the heartbeat behavior enabled only if you want ongoing relationship monitoring, and disable or remove the skill if periodic state updates are not desired.
If you choose to run the optional `npx` command, you may execute or install code that was not part of the reviewed skill artifacts.
The optional broader-framework installation points users to an external package command outside this instruction-only skill.
Install the full framework: `npx get-claudia`
Treat the optional Claudia framework install separately: verify the package and GitHub source, prefer pinned versions where possible, and only run it if you intentionally want the broader framework.