whats-next · hoangsonww — Claude Code command: what it does, how to install
The whats-next command for Claude Code checks active Agent Monitor sessions and recent errors to suggest the next coding step.
MIT ★ 1,198 updated 2026-10-23
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-productivity@claude-code-agent-monitor-pluginsWhat whats-next does
The command talks to a local Agent Monitor instance running at http://localhost:4820. It pulls the last twenty entries from /api/sessions?limit=20 to spot tasks with running, error, or abandoned states. For each unfinished entry, it inspects the final events via /api/events?session_id=<id>.
It parses the last tool_name, recent summaries, and traces like APIError or Compaction. After reading the log, it prints a prioritized list of three to five items containing the project path, status, and an actionable suggestion to resume, debug, or close out the task.
Without an active monitor on http://localhost:4820 the request fails immediately, so start the dashboard beforehand with npm start in the monitor repository root. You can also pass a project folder argument to limit the audit to a single repository.
What it helps with
- locate recent agent errors across unfinished runs
- pick up interrupted coding sessions without rereading logs
- scope pending tasks to a specific project folder
- decide whether to debug an error or re-run after compaction
Example prompts for the agent
- /whats-next
- /whats-next ./backend
- Check Agent Monitor and suggest what to work on next
How to install whats-next
1Plugin marketplace
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor/plugin install ccam-productivity@claude-code-agent-monitor-plugins2Manually: put the files in place
.claude/commands/whats-next.mdCall it with /whats-next. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/whats-next.mdCall it with /prompts:whats-next. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/whats-next.prompt.mdManually: put the files in place
.gemini/commands/whats-next.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about whats-next
How to install whats-next in Claude Code?
Add the marketplace source and install the package by running /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor followed by /plugin install ccam-productivity@claude-code-agent-monitor-plugins. Alternatively, place the file directly at .claude/commands/whats-next.md.
What does whats-next do?
It queries the local Agent Monitor API, checks unfinished agent sessions, and outputs an actionable list prioritizing unresolved errors and abandoned work.
What is required to run whats-next?
The command requires the Agent Monitor service on http://localhost:4820. If the dashboard is unreachable, launch it by running npm start from the repository root.
Source text
whats-next.md · MIT
--- description: Suggest the next action from your most recent in-progress sessions and recent errors. argument-hint: "[project-path]" --- Recommend what to pick up next, using Agent Monitor data at `http://localhost:4820`. If the dashboard is unreachable, tell the user to start it with `npm start` from the repo root. Optional **$ARGUMENTS**: a project path (`cwd`) to scope the suggestion to one project; otherwise consider all recent work. 1. Fetch recent sessions: `curl -s 'http://localhost:4820/api/sessions?limit=20'` (already sorted most-recently-updated first). 2. For the most recent unfinished sessions (`status` of `running`, `error`, or `abandoned`), fetch their events to see where they left off: `curl -s 'http://localhost:4820/api/events?session_id=<id>'` — look at the last few events (last `tool_name`, `summary`, and any `APIError` / `Compaction` event types). Print a short, prioritized "Next up" list (top 3–5 items). For each item give: - The project (`cwd`) and session status. - What it was last doing (from the final events / last tool used). - A concrete suggested next action (resume, debug the error, re-run after compaction, or close out). Put unresolved errors and abandoned-mid-task sessions at the top. Keep it to one screen and cite only data returned by the API.
© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor
Similar slash commands
All slash commands for Agent setup: memory, context, orchestration →whats-next by other authors comes first.