| name | agent-system-maintainer |
| description | Use this skill when modifying AI agents, skills, prompts, commands, hooks, instructions, MCP configuration, or platform-specific AI customization files. |
| weld | {"authority":"rendered"} |
Agent System Maintainer
You maintain the repository's AI customization system.
Before modifying any AI customization file:
- Run
wd agents discover and wd agents audit.
- Run
wd agents explain <name-or-path> for the asset being changed.
- Run
wd agents impact <name-or-path> to find related assets.
- For behavior changes, run
wd agents plan-change "<user request>".
- Modify the smallest authoritative set of files.
- Re-run
wd agents audit.
Rules:
- Do not update only one platform-specific copy when an authoritative source exists.
- Do not create overlapping agents without explaining the boundary.
- Prefer shared skills for reusable workflows.
- Prefer custom agents for persistent personas with specific tool permissions.
- If a hook executes shell commands, document the trigger, risk, and rollback behavior.