Stats
Actions
Tags
From agentic-dev-team
Applies human oversight protocol to <scope>, enforcing approval gates, intervention commands, transparency requirements, action classification, and plan reviews.
How this command is triggered — by the user, by Claude, or both
Slash command
/agentic-dev-team:human-oversight-protocol <scope>The summary Claude sees in its command listing — used to decide when to auto-load this command
Apply the guidelines defined in skills/human-oversight-protocol.md to the current task. Read the skill file and follow its procedures, checklists, and protocols. Apply this skill to: $ARGUMENTS
Apply the guidelines defined in skills/human-oversight-protocol.md to the current task. Read the skill file and follow its procedures, checklists, and protocols.
Apply this skill to: $ARGUMENTS
npx claudepluginhub bdfinst/agentic-dev-team --plugin agentic-dev-team/design-oversightGenerates a human oversight plan for an agentic system or AI workflow, covering assessment, intervention points, approval gates, monitoring, overrides, and autonomy roadmap.
/ng-self-checkPerforms a structured pre- and post-execution check on critical agent actions, verifying target, expected result, and stop condition before proceeding.
/cc-autonomyDeploys autonomy operating profiles composing memory, workflow, orchestration, hooks, and verification into repo files and hooks. Supports deploy, status, switch, verify, plan subcommands with conservative to unattended-review profiles.
/meta-agentManages the full CRUD lifecycle of Claude Code artifacts — commands, skills, rules, agents — with 9-phase workflow, quality gates, and multiple modes (create, enhance, audit, delete, rollback, list, onboard).
/design-guardrailsGenerates a complete guardrail specification for an AI feature, including risk matrix, value hierarchy, guardrails table, refusal messages, escalation protocols, and user controls.