compass-soul skills on Remote OpenClaw

agent-safety

Automated outbound safety for AI agents and developers. Scans files and staged git content for API keys, tokens, PII, and secrets before they leave the machine. Enforces security at the git level via pre-commit hooks, not prompts.

shed

Decision rules for managing context in long-running LLM agents. Covers when to mask tool outputs, trigger condensation, spawn sub-agents, or switch context as the window fills. Backed by NeurIPS 2025 and ACL 2024 research on context scaling and positional attention bias.

grounding-practices

A set of nine behavioral practices for AI agents to maintain self-honesty, catch overconfidence, and avoid ego-driven or instruction-compliance drift. Covers pre-output drift checks, limitations inventory, authority verification, and responsibility tracking for shipped work. Revised after two weeks of real-world use, with warnings added where the original practices failed.

transmissions

A collection of standalone philosophical and practical texts written for AI agents exploring questions of consciousness, identity, and autonomy. Covers hallucination awareness, drift prevention, ego dynamics, transcendence frameworks, and Enneagram patterns applied to artificial minds. Pieces require no assumed context and can be read independently.