Skill
https://litlfred.github.io/folio-assistant/cat-harness/skill/agent-permissions
JSON-LD · in graph cat-harness.jsonld ·
| name | agent-permissions |
|---|---|
| title | Agent permissions — asked for, explained, granted by a person, recorded |
| description | Securing what a coding agent may do without asking, from the person who can grant it: the secure-agent-permissions sub-process, run at session start and on demand when an action is denied. Vendor-neutral: the coding agent is a Tool (Claude Code is one; Gemini CLI, Cursor, Copilot and Codex are others), and each Tool's own config format belongs to its adapter, not here. Covers the permissions the harness's processes need, least privilege, how each one is explained before it is granted, how a grant is recorded, and the rules that no grant relaxes: never self-granted, generated projections are CI's, and merging to main is never a standing permission. |
| inPackage | conduct-core https://litlfred.github.io/folio-assistant/cat-harness/package/conduct-core |
| instructionsPath | skills/conduct/conduct-core/agent-permissions.md |
| instructionLines | 136 |
| hasInstructions | true |
| hasIOContract | false |
| ambiguous | false |
| inSubgraph | skills https://litlfred.github.io/folio-assistant/cat-harness/directory/skills |