Persistent proactive self-improving AI teammates with memory, skills, and schedules.
Skill Claude CodeCodex
Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…
Skill Claude CodeCodex
Use when work reaches a GitHub-hosted issue, pull request or review, release, tag, or live deployment-branch boundary, including indirectly after investigation, completed development, or repository policy requires delivery. Also trigger when work discovers a repository defect that may need duplicate search or an issue…
Skill Claude CodeCodex
Use when managing this agent, any other agent in its Rundesk install, or the install itself. It supplies verified operational workflows and safety rules for agent instructions, gateways, conversations, channels, schedules, providers, skills, backups, configuration, credentials, and the Rundesk lifecycle. Do not use…
Skill Claude CodeCodex
Use when creating, modifying, reviewing, testing, or publishing a Rundesk skill, including reusable workflow scripts and external integrations. It supplies compact authoring, behavioral verification, and catalog publication. Do not use it to perform an existing skill's workflow or write one-off project automation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: