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 skills add Xwen0857/agent-orchestrator --skill worker-deliverygit clone --depth 1 https://github.com/Xwen0857/agent-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xwen0857/agent-orchestrator/worker-delivery)<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/worker-delivery"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/worker-delivery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/worker-delivery"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/worker-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00029 | $0.02704 |
| Opus 5 | $0.00015 | $0.01352 |
| Sonnet 5 | $0.00006 | $0.00541 |
| Haiku 4.5 | $0.00003 | $0.00270 |
Grade A, and why
worker-delivery 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 9d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worker Delivery
V2 基线(强制优先)
- worker-delivery 进入任务前必须读取
templates/coordination/tasks/task_folders/<task_id>/meta.json,并确认状态为ASSIGNED或IN_PROGRESS。 ASSIGNED -> IN_PROGRESS由scheduler-ops推进;worker 只消费已装配的worker_runtime_view.json并提交执行结果。IN_PROGRESS -> TESTING的推进仍由编排流控制并记录到log.ndjson。- token budget lane、reclaim、rebuild、keeper candidate routing 由
scheduler-ops/ runtime control 拥有;worker 不直接执行 budget hard-stop 或写BLOCKED_PENDING_APPROVAL。 - 发生歧义时必须写
clarification_request.md并将状态置为BLOCKED_AWAITING_CLARIFICATION,不得静默等待。 - 运行态
worker_tasks/<worker_id>_tasks.md位于仓外状态目录;templates/coordination/tasks/<worker_id>_tasks.md仅作兼容镜像,不作为真实状态读写依据。 - worker 当前只回写 convergence、局部协作消息和交付证据;
meta.consumption与知识库检索仍由其他运行时路径负责,未在 deterministic worker 内实现时不得在文档中假定其已存在。 - 当
keeper_enabled=true时,worker 不得直接写入knowledge-base/entries;经验候选由scheduler-ops基于 runtime signal 提交到 keeper 队列。 dispatch.role_type表示编排运行角色(如worker-delivery、tester-ephemeral);实施用途角色的正式分类由implementation_topology.coarse_template_role表示(如frontend、backend、database),implementation_topology.role_layer仅保留为兼容投影,二者不得与编排角色混用。- lifecycle policy 由
scheduler-ops/ runtime assembler 选择并投影为worker_runtime_view.json.lifecycle_governance;worker 只消费该视图以及其中的workerStage下行分配,不拥有治理真相,也不持久化 policy authority。 - wrapper 通过
ORCH_WORKER_STAGE_*环境变量把workerStagecontract 投影给 handler;这些变量只是运行注入接口,不代表独立 authority。 implementation_topology.coarse_template_role是 topology config 下行后的正式 coarse template classification;implementation_topology.role_layer仅保留为兼容投影。selected_template是由 topology 驱动自动解析出的细模板结果,而不是 worker 侧需要重新决策的一层。
核心职责
- 根据
task_id与 worker 指令完成实现,确保交付范围不越界。 - 产出可复现的交付记录:改动清单、关键命令、结果摘要与风险说明。
- 在交付后向 task-cluster mailbox 发布结构化协作消息,并为 tester 验收保留可消费产物。
- 在验收前不得声明完成;验收失败时按反馈进行修复并重新交接。
- 持续回写
worker_convergence与局部协作信号,供 scheduler/ops/keeper 消费。 - 所有可离开
workerStage的交付物必须先经过 wrapper export,并形成delivery.export-records.json供 tester/runtime 后续消费。
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.
- 9d ago First seen · 131 lines · 29 tokens per session scan A d6e0360dd004
worker-delivery is a skill published in the GitHub repository Xwen0857/agent-orchestrator (2 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 2,704 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
clawteam
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages between agents, monitor progress via kanban board, or launch pre-built team templates (hedge-fund, code-review…
ClawTeam
This skill should be used when the user asks to "create a team", "spawn agents", "assign tasks", "coordinate multiple agents", "check team status", "view kanban board", "send messages between agents", "manage team tasks", "monitor team progress", or mentions "clawteam", legacy "oh", "multi-agent coordination", "team…
status
A workflow skill that summarizes project status and progress from workflow.json and milestones.json files.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
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.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.