Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mvschwarz/openrig/queue-handoffnpx skills add mvschwarz/openrig --skill queue-handoffgit clone --depth 1 https://github.com/mvschwarz/openrigWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00094 | $0.02681 |
| Opus 5 | $0.00047 | $0.01340 |
| Sonnet 5 | $0.00019 | $0.00536 |
| Haiku 4.5 | $0.00009 | $0.00268 |
Grade A, and why
queue-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Handoff
Durable work handoff via queue items. Lets the system keep moving through compactions, missed messages, and interruptions by passing the ball forward instead of leaving work suspended in chat or in-flight without an owner.
Use this when
- Ending a turn on substantive work. Active work should end by passing the ball to an owner or to the human — never by going idle with the rig appearing dormant.
- Finishing a slice that has a clear next step. Default-nudge: receiver gets a wake-ping plus the durable queue item.
- Blocked on another agent's work. Park the qitem with
closure_reason: blocked_onand the blocker qitem id. - Escalating to the human. Make the escalation a durable attention item, not just a chat message.
Don't use this when
- The work is genuinely complete and there's no follow-on owner. Use
closure_reason: no-follow-on(terminal completion) orcanceled/deniedas appropriate. - The handoff would be too small and turn work into bureaucracy. Bundle the work into a coherent slice instead of decomposing every step.
- The handoff would be too broad and lose ownership/proof/closure criteria. Shape the qitem so the receiver knows the expected next action and closure evidence.
The hot-potato terminal-turn-rule
Active work ends by passing the ball to a named next owner or to the human. The qitem state machine enforces this:
pending → in-progress → done requires closure_reason from one of:
handed_off_to— work continues at a different seat (target = new owner)blocked_on— parked pending another qitem (target = blocker qitem id)denied— receiver rejected the workcanceled— sender or receiver withdrewno-follow-on— terminal completion, nothing else neededescalation— kicked up to a higher tier (target = escalation target)
Three of those (handed_off_to, blocked_on, escalation) additionally
require closure_target. The daemon enforces this at the domain layer;
every surface (CLI, MCP, future UI) inherits the same guarantee.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 193 lines · 94 tokens per session scan A c38a5b814158
queue-handoff is a skill published in the GitHub repository mvschwarz/openrig (64 stars, last pushed 3d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,681 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
cao-supervisor-protocols
Supervisor-side orchestration patterns for assign, handoff, and idle inbox delivery in CAO.
autoprompt
Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…