How do I install the Openclaw Mem Self Model skill?

Run npx skillmds@latest add phenomenoner/openclaw-mem-self-model in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Openclaw Mem Self Model skill do?

Inspect and govern the experimental derived self-model sidecar. Use for continuity snapshots, attachment maps, drift, threats, public-safe wording, release receipts, or migration comparisons. It is listed under AI & ML on SkillMD.

Is Openclaw Mem Self Model safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Mem Self Model?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openclaw Mem Self Model free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openclaw Mem Self Model?

phenomenoner (@phenomenoner) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openclaw Mem Self Model by phenomenoner

Name: Openclaw Mem Self Model
Rating: 4.2 (5 reviews)
Author: phenomenoner

File contents

Self-model Lab

The sidecar is derived, editable, and rebuildable. It is not consciousness, identity truth, or a second memory owner. Never write its claims back into Store truth automatically.

Workflow

Build current for a scoped audit point.
Inspect attachment and adjudication before release decisions.
Check threat feed, explanation, and sensitivity before stronger wording.
Run wording lint before continuity-facing copy.
Use release only with a concrete operator reason; rebuild current to verify effect.

openclaw-mem continuity current --scope <scope> --session-id <session> --json
openclaw-mem continuity attachment-map --snapshot <snapshot> --json
openclaw-mem continuity adjudication --snapshot <snapshot> --json
openclaw-mem continuity threat-feed --snapshot <snapshot> --json
openclaw-mem continuity public-summary --snapshot <snapshot> --json
openclaw-mem continuity wording-lint --snapshot <snapshot> --json
openclaw-mem continuity release-history --scope <scope> --session-id <session> --json

Persona priors are hints, not sovereignty. If evidence is thin or prior-dominated, report instability instead of inventing certainty. Enable autonomous receipts only when explicitly requested; use the governed soak controller under <workspace> for long gates.

Verify

openclaw-mem continuity status --json
python -m pytest tests/test_self_model_sidecar.py -q
git diff --check

Frequently asked questions

Openclaw Mem Self Model