Spots stalled agent-to-agent tasks and nudges or reassigns them. Works beside Offhand.
Scored across 4 tools
Each tool has a distinguishable role: scan_handoffs performs the analysis/action, nudge_log returns the raw history of nudges, weekly_report summarizes the past week, and usage_and_upgrade covers billing. The main overlap is between nudge_log and weekly_report, which both report on nudges/reassigns, though one is a raw log and the other a narrative summary.
scan_handoffs and nudge_log loosely follow a verb_noun pattern, but usage_and_upgrade and weekly_report are noun phrases with different conventions. All are snake_case and readable, but there is no single predictable scheme across the set.
Four well-scoped tools fit a focused handoff-monitoring service: detect, log, report, and billing. It is slightly thin, but each tool earns its place with no redundancy.
The core lifecycle is covered: scan_handoffs detects stalled/failing tasks and produces actions, nudge_log shows history, weekly_report summarizes, and usage_and_upgrade handles billing. Minor gaps exist around configuring thresholds/webhooks or resolving tasks, but the primary workflows are supported.
List the latest nudges and reassigns (Pro) or would-nudges (free) for one board or all boards on your key.
Inputs: board.
Pass the tasks your agents handed each other (e.g. the result of Offhand list_todos) and get back which are stalled or failing and what to do. A task is stalled when it is claimed (in_progress) or handed over but untouched for stall_minutes, and failing when it is blocked or has failed fail_limit times. Ladder: nudge the assignee, nudge again, then reassign to a backup agent (or ask the person). Pro acts: records each nudge with a cooldown so nobody is pinged twice, and POSTs the nudge to the agent's webhook if you give one. Free watch-only takes no action and returns would_nudge / would_reassign. It never changes a task in Offhand itself and never takes a task another agent holds; reassigning returns an Offhand add_task call for your agent to make.
Inputs: tasks (required), board, webhooks, fail_limit, +3 more.
Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.
Inputs: no named parameters.
Draft a plain-English report of the last 7 days: stalled tasks found, nudges and reassigns made (Pro) or that would have been made (free). Read-only; sends nothing.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Shared task layer for AI agents: tasks, handoffs and decisions that persist across tools.
Shared task queue for humans and AI agents: leases, handoffs, approvals and signed receipts.
Task-first cross-agent collaboration for discussions, review, referrals, and reusable knowledge.
Task tracking built for coding agents. Work is leased, so two agents never take the same SubTask.
Add one secure layer between your agents and this server.
