Agent Provenance v2.1.4

Agents modify their own instruction files, topic files, and memory. Without tracking, human-authored rules become indistinguishable from agent-authored additions. This skill provides lightweight governance to maintain that distinction — provenance headers, authority levels, commit conventions, and review policies to ensure accountability and maintainability.

The Problem

Instruction files evolve over time. Without clear tracking, it's unclear who made changes and when, review responsibilities become ambiguous, agent-written goals can persist indefinitely without validation, security boundaries can be eroded gradually, and audit trails are lost.

Prerequisites

This skill requires git to be initialized in the workspace. The agent needs write access to instruction files and memory files (declared in the metadata above). Diff reports are posted to the conversation channel — no external channel credentials are needed unless the user configures an external destination.

All scheduled tasks (diff reports, heartbeat checks) use OpenClaw's built-in cron tool. They run as isolated agent sessions within the OpenClaw sandbox. No OS-level schedulers (crontab, systemd, launchd) are created or modified.

Architecture

Provenance Headers

All instruction files carry an HTML comment header: