Lionclaw private context
Lionclaw is a local control plane for AI coding agents. It runs AI agents as durable, auditable workers with explicit state, skills, channels, schedules, and bounded permissions.
npx -y skills add moshthepitt/lionclaw --skill lionclaw-private-contextAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Host-side LionClaw private-context skill for deterministic projection, committed-turn recording, and explicit profile or memory management.
SKILL.md
1.2 KB, as published. Nobody here has run it
LionClaw Private Context
Use this skill as LionClaw's default local private-context capability. It owns a host-only SQLite store and exposes three deterministic surfaces:
scripts/projector: pre-prompt private-context projection.scripts/recorder: post-turn recording from committed LionClaw transcript records.scripts/context: manual operator inspection, correction, deletion, and audit.
The runtime never receives direct access to the store. Projected context is advisory prompt context only, and LionClaw core remains the final authority for trust tier, prompt policy, budgets, rendering, and audit.
Do not infer profile or memory facts from arbitrary conversation. Store exact committed turns for episodic recall, and create durable profile or memory records only from manual operator commands or explicit user directive lines:
remember: <text>style: <text>preferences: <text>
The skill must stay deterministic: no model calls, no embeddings, no runtime DB access, no LionClaw core DB reads, and no hidden transport or channel logic.