agent framework commands

microsoft/agent-governance-toolkit

Command

Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.

microsoft/agent-governance-toolkit

Command

Show the active AGT governance status for this Claude Code session.

inclusionAI/AWorld

Command

Provide a code review for the given pull request.

inclusionAI/AWorld

Command

This is a placeholder command definition for plugin framework tests.

agentlas-ai/Agentlas-OS

Command Claude Code

Build, repair, or package Agentlas agents and teams with Hephaestus.

agentlas-ai/Agentlas-OS

Command Claude Code

Agentlas commands — one entry point for network, build, storm, call, and the rest.

agentlas-ai/Agentlas-OS

Command Claude Code

Use the Agentlas browser hardpoint for browser-required work.

DougTrajano/pydantic-ai-skills

Command Claude Code

Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.

CronusL-1141/AI-company

Command

A command that checks whether the AI Team OS project has the Python version, configuration files, services, database, hooks, and dashboard dependencies it needs.

CronusL-1141/AI-company

Command

A command for viewing the current state of an AI Team OS project, including teams, agents, and active meetings.

CronusL-1141/AI-company

Command

A command that checks and starts the AI Team OS API server and dashboard. An API server provides data and operations to other programs, while a dashboard is a web interface for viewing and using the system.

ucsandman/DashClaw

Command Claude Code

Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates → triage → parallel worktree fixes → verify → ship. The goal prompt that drives the dashclaw-find-and-fix workflow.

ucsandman/DashClaw

Command Claude Code

Officially retire the published dashclaw/legacy Node SDK the safe way — deprecate now, delete at v5 — without breaking external npm consumers. Drives the legacy-sdk-deprecation-sweep workflow.

ucsandman/DashClaw

Command Claude Code

Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMORY.md health, and PROPOSE (never apply) CLAUDE.md/memory edits for human approval.

BlackBeltTechnology/pi-agent-dashboard

Command

Abort the running flow on a session. Usage /dashboard:flow-abort.

BlackBeltTechnology/pi-agent-dashboard

Command

Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.

BlackBeltTechnology/pi-agent-dashboard

Command

List git branches for the current dir (current marked ). Runs locally, no LLM.

DemonDamon/AgenticX

Command Cursor

A Git command for copying selected, finished commits from one branch onto another with `cherry-pick`, which reapplies those exact changes.

iii-experimental/agentos

Command

Quick evolve a function — generate, register, and evaluate.

iii-experimental/agentos

Command

Show AgentOS system status — agents, workers, health.

iii-experimental/agentos

Command

Launch the AgentOS TUI dashboard.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/app-init.md.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/bootstrap.md.

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/spec-intake.md.