compound
01Command
Review conversation, propose compounding improvements, and apply them.
50 tagged agent workflows, measured the same way as everything else here.
Browse within: agent-runtime 12ai-coding-agent 12developer-tooling 12agent-harness 9agent-workbench 9agentic-coding 9antigravity 9opencode 9operations 9claude-ai 5claude-desktop 5
Command
Review conversation, propose compounding improvements, and apply them.
Command
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Command
Review OpenCode session history for a project and propose the best skills, agents, and command architecture.
Command
Draft a Conventional Commit message from the staged git diff.
Command
Purpose: Turn any concept or document into a live, adversarial interview drilling session, tailored to a specific role and interview format.
Command
Use when an agent should investigate a defect, regression, flaky test, or incident-like failure with evidence, hypotheses, verification, and recurrence prevention.
Command
Use when an agent should run a Discover -> Define -> Develop -> Deliver workflow before implementing a meaningful feature.
Command
Use when an agent should autonomously escalate a hard task into a recursive session, prefer Typed RLM first, and only fall back to bounded structured analysis when needed.
Command Claude Code
Full memory flush — refresh state.md, append to activity log, route any new decisions/insights, then commit and push.
Command Claude Code
Append a new entry to the activity log for this session.
Command Claude Code
Set up a new project (client / internal-product / tool), retrofit an existing folder to the template, or reconcile a folder's memory after a thread loss.
Command
Enable, disable, or report Agent Workflow Kit ultracode mode.
Command
Show Agent Workflow Kit workflow progress events.
Command
Run the requested Agent Workflow Kit workflow.
Command Claude Code
Propose unused or redundant harness cleanup without deleting automatically.
Command Claude Code
Configure Tink language, install scope, git tracking, and hook policy.
Command Claude Code
Run the checks promised in the current Tink contract and record evidence.
Command Claude Code
Run Alcove's AI quality eval across smoke, real integrations, and agent-facing flows.
Command Claude Code
Run Alcove's high-cost real external integration smoke.
Command Claude Code
Run Alcove's isolated local smoke suite.