Stats
Actions
Tags
From Agent Flow
Workspace dashboard: lists every active framework run across all primitives, highlights blockers (stuck items, exhausted auto-continue caps), shows cumulative cost, and suggests the next action. The natural command to run after re-opening Claude Code in a workspace with in-flight runs, or whenever the user wants a one-shot overview of "what's going on". USE this skill when: - the user has just (re)opened the workspace and wants to know what is in flight; - the user says "what's going on", "show me everything", "any active runs", "where are we", "any pipelines running"; - the user wants a one-shot health check + suggested next action. DON'T use this to inspect a specific run in depth (use `/agentflow:inspect show <id>` or `tree <id>`), or to modify state (board is read-only). Explicit: `/agentflow:board` or `/agentflow:board --json`.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentflow:board [--json] [--no-failed][--json] [--no-failed]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Surface the workspace's current state in one screen. Read-only, no mutation.
Surface the workspace's current state in one screen. Read-only, no mutation.
node "${CLAUDE_PLUGIN_ROOT}/dist/inspect.js" board [--json] [--no-failed]
N active, M done, K failedforeach: 12/30, pipe: 2/4 stages, iterate: 3/10 iters), plus the parent run if it is a /agentflow:pipe childin_progress from a dead session, auto_continues cap exhausted, etc.--no-failed): runs that ended in failed status, with error previewpipe drive, inspect tree, state/foreach.js reset, etc.After (re)opening Claude Code in this workspace:
user: /agentflow:board
assistant: (calls the CLI, surfaces the output)
If something is active, sending any next message will trigger the Stop hook at end-of-turn and auto-resume the work. /agentflow:board does not resume anything itself — it only reports.
/agentflow:runs — the writable sibling: pause/resume one job or the whole engine, set priority (queue order), delete a run, or clean up finished ones. Board reports; runs controls./agentflow:inspect runs: /agentflow:board is for the "session start" overview with suggestions; /agentflow:inspect runs is the bare tabular listing. /agentflow:board is opinionated, /agentflow:inspect is plumbing.npx claudepluginhub alesaiani/agentflow --plugin agentflowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.