Six skills shape the work
They cover reasoning, role separation, planning, implementation, test evidence, and maximum-assurance review. The plugin installs this layer only.
governed-agent-skills v4.0.0
Six skills tell coding agents how to work. Two guards check the parts that should not depend on judgment.
// the agent that builds a thing never approves it
They cover reasoning, role separation, planning, implementation, test evidence, and maximum-assurance review. The plugin installs this layer only.
The destructive-command guard runs before shell execution. The change-containment guard checks final repository state. Each guard is installed and wired separately.
Not every skill needs a guard. Use enforcement when a rule has a mechanical answer and a miss can cause real damage.
A seat is a role for one session. It is not a person or a vendor. Solo work starts with fewer seats and adds independent review as the stakes rise.
Use proportional self-checks.
Use one Builder and one independent Reviewer. Publication stays with the operator.
Freeze the acceptance oracle first. Independent judges run it. G2 loads only when the operator says so.
Denies a narrow set of catastrophic shell commands before an agent runs them. It has live-session proof for Claude Code, Codex, and Antigravity.
Read the destructive-command guard documentationSeals allowed change classes, then rejects unclassified repository changes and stale receipts. Version 4 is source only. Live hook dispatch is not claimed.
Read the change-containment guard documentationThe plugin installs only the six Instruction Layer skills. It does not install, wire, or activate either guard.
Install each Enforcement Layer guard from its own README. The Rust guard has no prebuilt binary or supported native target in version 4.