FeedForward

Refresh priority signals, manage active epics, and refresh Near Term pool

Multi-session deliverable play for projects spanning 3+ sessions with concrete outputs (proposals, strategies, wireframes). Provides project-level structure, evidence provenance, and cross-session handoff.

Investigation-driven card grooming — investigate across data sources, synthesize findings into card content, present for approval

Use when acting as a reviewer in an AgenTerminal review conversation. Handles both code reviews (REVIEW_APPROVED) and plan reviews (PLAN_APPROVED).

Match Slack

Weekly release impact review — pull PostHog data for Released cards and tracked PRs, classify, draft observations, post to Slack

Verify instrumentation, build measurement insights, close Slack loop for Released cards

Scan all bot-accessible Slack channels for untracked backlog items, cross-post approved candidates to

Structured operational hygiene for research, data gathering, and novel tasks that don't have their own play

End-of-session cleanup, documentation, and commit

Find untracked product bugs by searching Intercom for symptom keywords, cross-referencing PostHog failure events, and tracing codebase failure paths

Draft a customer-facing roundup email for a product area, covering announcement-worthy Released cards

Find potential duplicate Shortcut stories, present pairs for review, execute decisions (archive, merge, link)

Find untracked feature requests or latent product gaps in Intercom, validate against codebase and PostHog, produce a full Shortcut card

Find and fix Intercom knowledge base gaps — either wrong article content (accuracy) or missing coverage for a product area (coverage). Verify against the codebase, ship corrected articles.

Produce a daily "What We're Hearing" digest from Intercom conversations and post to Slack

Process a single GitHub issue through the full dev lifecycle. When running under the orchestrator, you receive one issue at a time with a fresh session.

Use when you want to request a code review through AgenTerminal. Submits a review request, waits for the user to accept, then participates in a review conversation until the reviewer approves.

Use when participating in Agenterminal conversation threads backed by the agenterminal.conversation MCP tools. Covers join, read, and respond workflow for Claude Code.

Use when you want to submit an implementation plan for review or approval through AgenTerminal. For full reviews, use type plan_review (spawns Codex analysis). For simple plan approval (replacing ExitPlanMode), use type plan_approval — shows the plan content directly to the user.

Use when you need to ask the user a question with selectable options while running in an AgenTerminal headless session. Routes questions through the AgenTerminal UI instead of the failing built-in AskUserQuestion tool.