# Manage Governance

> Manage governance policies for skills in config/governance.yaml. Set, remove, or list usage policies.

- **Type:** Skill
- **Install:** `agentstack add skill-skill-mill-agent-skill-harbor-manage-governance`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skill-mill](https://agentstack.voostack.com/s/skill-mill)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skill-mill](https://github.com/skill-mill)
- **Source:** https://github.com/skill-mill/agent-skill-harbor/tree/main/.claude/skills/manage-governance
- **Website:** https://skill-mill.github.io/agent-skill-harbor-demo

## Install

```sh
agentstack add skill-skill-mill-agent-skill-harbor-manage-governance
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Manage Governance Policies

You are managing governance policies for the Agent Skill Harbor catalog.

## File

- **Config**: `config/governance.yaml`
- **Zod schema**: `web/src/lib/schemas/governance.ts`

## Schema

```typescript
usagePolicySchema: 'recommended' | 'discouraged' | 'prohibited' | 'none'

governancePolicySchema: {
  usage_policy: UsagePolicy
  note?: string
}

governanceSchema: {
  policies: Record  // key = skill path
}
```

## Key Format

Skill path key: `github.com/{owner}/{repo}/{skill-file-path}`

Examples:
- `github.com/example-org/code-review/.claude/skills/review/SKILL.md`
- `github.com/anthropics/prompt-library/SKILL.md`

## Actions

Parse the user's intent and execute the appropriate action below.

### Set Policy

When the user wants to set a governance policy (e.g., `govern github.com/owner/repo/SKILL.md recommended "reason"`):

1. Read `config/governance.yaml`
2. Find or create an entry under `policies` with the skill path key
3. Set `usage_policy` to one of: `recommended`, `discouraged`, `prohibited`
4. Optionally set `note`
5. Write back `config/governance.yaml`

### Remove Policy

When the user wants to remove a governance policy or set it to `none`:

1. Read `config/governance.yaml`
2. Remove the entry from `policies`
3. Write back `config/governance.yaml`

### List Policies

When the user wants to list governance policies:

1. Read `config/governance.yaml`
2. Display a table with: skill path, usage_policy, note

## Important Notes

- All changes are made to local files only
- Remind the user to create a PR to apply changes
- After making changes, run `pnpm run build:catalog` to regenerate the catalog

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skill-mill](https://github.com/skill-mill)
- **Source:** [skill-mill/agent-skill-harbor](https://github.com/skill-mill/agent-skill-harbor)
- **License:** MIT
- **Homepage:** https://skill-mill.github.io/agent-skill-harbor-demo

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skill-mill-agent-skill-harbor-manage-governance
- Seller: https://agentstack.voostack.com/s/skill-mill
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.