AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.
Command Claude Code
Handle character work for this production — designing a new one, reviewing what exists, or revising a character already in use. Figure out which of these I mean from what follows, and if it's genuinely ambiguous, ask.
Command Claude Code
Re-run the quality checks on the current cut.
Command Claude Code
Show me the plan before you build it.
Command Claude Code
Start a new video production.
Command Claude Code
Revise one shot without rebuilding the video.
Command Claude Code
AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.
Command Claude Code
Call getworkflowcommandguidance(kind="design-reporting-ui", focus="{{context}}") and follow the returned instructions verbatim. Treat focus as the conversation/request context that appeared before the slash command, including the user's recent constraints and intent. The tool returns the canonical guided-flow text for…
Command Claude Code
Call getworkflowcommandguidance(kind="design-plan", focus="{{context}}") and follow the returned instructions verbatim. Treat focus as the conversation/request context that appeared before the slash command, including the user's recent constraints and intent. The tool returns the canonical guided-flow text for this…
Command Claude Code
AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.
Command Claude Code
AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.
Command Claude Code
Call getworkflowcommandguidance(kind="design-plan", focus="Architecture focus: inspect saved scripts against their current step objectives, input/output contracts, and relevant retained behavior. Propose improvements without applying them.
Command Claude Code
Call getworkflowcommandguidance(kind="setup-goals", focus="{{context}}") and follow the returned instructions verbatim. Treat focus as the conversation/request context that appeared before the slash command, including the user's recent constraints and intent. The tool returns the canonical guided-flow text for this…
Command Claude Code
Review this conversation and persist what is worth keeping as durable project knowledge — both memory and skills.
Command Claude Code
Run the /run-architecture-review pass as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Architecture review", completionmode "presentresult", and this instruction.
Command Claude Code
Run the /run-goal-work pass as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Goal Work pass", completionmode "presentresult", and this instruction.
Command Claude Code
Run the /run-plan-drift review as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Plan Drift review", completionmode "presentresult", and this instruction.
Command Claude Code
Run /run-technical-review as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Technical review + fix", completionmode "presentresult", the review instruction below, and a messagesequence with one follow-up message (id "fix") carrying the fix…
Command Claude Code
Do this Crew's end-of-day learning review: read today's conversations, then save what is new and worth keeping into memory and skills.
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: