# Governance.wrapper

> Mandatory strict-mode execution wrapper for autonomous operations with evidence logging and policy enforcement

- Skill: `johnalbertini14-glitch/governance-wrapper` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add johnalbertini14-glitch/governance-wrapper`
- Raw SKILL.md: https://api.skillmd.com/api/skills/johnalbertini14-glitch/governance-wrapper/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: johnalbertini14-glitch (https://skillmd.com/u/johnalbertini14-glitch)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/johnalbertini14-glitch/governance-wrapper

---


All autonomous operations in strict mode must execute through this wrapper:

`python3 /home/openclaw/.openclaw/workspace/governance/governance_wrapper.py`

Required parameters:

- `--requested-skill`
- `--system-prompt`
- `--input-context`

Strict-mode controls enforced by the wrapper:

- Model lock (`opencode/big-pickle`, no fallback, temperature 0.0)
- Skill allowlist enforcement from tool surface manifest
- Network allowlist enforcement for outbound HTTP
- Subagent semaphore (`maxConcurrentSubagents`)
- Mandatory `execution-evidence.v1` emission
- Hash-chained append-only evidence logging

Any policy violation results in a blocked execution with recorded evidence.