Applying a permission policy
Configures which OpenRig commands an AI coding agent may run without repeated approval prompts
- Repository
- mvschwarz/openrig
- Stars
- 8,553
- Licence
- Apache-2.0
- Files
- 1 file
What it does
When you set up an AI agent team with OpenRig, this skill helps the agent set the command permissions you choose in the tool that runs it, such as Claude Code or Codex. It explains the options, recommends keeping the safe team default, and only adds allow rules you explicitly approve, backing up files and avoiding duplicates. It also tells you that some lifecycle commands still ask for approval even after you say yes.
Great for
- Developers setting up OpenRig agent teams who want fewer repeated approval prompts
- Users who want a clear, reversible way to control which rig commands agents can run
Skip it if
- Anyone expecting fully prompt-free operation: the skill itself says native rules still prompt for lifecycle commands, installs, commits and writes outside writable roots
- Situations needing broad filesystem or network access without careful review, since the skill treats that as a separate explicit opt-in that widens exposure
Try asking
- “Before launching my team, set up the recommended permission defaults for OpenRig”
- “Remember the rig ps and rig queue list commands for this project so they stop prompting me”
- “Show me the permission options for my Claude Code seats and let me choose”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
applying-a-permission-policy.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip applying-a-permission-policy.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip applying-a-permission-policy.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Choose the narrowest scope that works, such as specific rig verbs like rig ps rather than the whole rig family, since a whole-family allow also covers lifecycle and topology commands.
- Review the diff the agent proposes and confirm which settings file it changes before accepting.
- After approving, start a new session or use the resume path if the agent says existing conversations won't load the change.
What's inside
- SKILL.md
Redistributed unmodified from mvschwarz/openrig under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.