worker-delivery

worker-delivery is a skill for Claude Code, Codex from Xwen0857/agent-orchestrator. It costs 29 tokens per session (2,704 once invoked), scanned A, original, MIT.

A delivery workflow for workers in a coordinated coding system. It defines how a worker receives an assigned task, records progress, handles unclear requirements, and submits evidence for testing.

In plain words
What is it for?
For carrying out assigned code or documentation work, reporting results, requesting clarification, and handing completed work to a tester.
Why use it?
It prevents workers from changing orchestration state or shared knowledge in the wrong way and makes task handoffs explicit.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit For carrying out assigned code or documentation work, reporting results, requesting clarification, and handing completed work to a tester.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xwen0857/agent-orchestrator/worker-delivery
Install

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.

Any agent
npx skills add Xwen0857/agent-orchestrator --skill worker-delivery
Clone the repo
git clone --depth 1 https://github.com/Xwen0857/agent-orchestrator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for worker-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/worker-delivery/github.svg)](https://agentmods.dev/skills/xwen0857/agent-orchestrator/worker-delivery)
Your own site
<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.

agentmods 80×15 button for worker-delivery

Your own site · 80×15
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash d6e0360dd004, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

worker-delivery/SKILL.md · 131 lines

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)

  1. 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 ASSIGNEDIN_PROGRESS
  2. ASSIGNED -> IN_PROGRESSscheduler-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
  3. 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
  4. 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。
  5. 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。
  6. 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。
  7. 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。
  8. dispatch.role_type 表示编排运行角色(如 worker-deliverytester-ephemeral);实施用途角色的正式分类由 implementation_topology.coarse_template_role 表示(如 frontendbackenddatabase),implementation_topology.role_layer 仅保留为兼容投影,二者不得与编排角色混用。
  9. 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。
  10. wrapper 通过 ORCH_WORKER_STAGE_* 环境变量把 workerStage contract 投影给 handler;这些变量只是运行注入接口,不代表独立 authority。
  11. 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

  1. 根据 task_id 与 worker 指令完成实现,确保交付范围不越界。
  2. 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。
  3. 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。
  4. 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。
  5. 持续回写 worker_convergence 与局部协作信号,供 scheduler/ops/keeper 消费。
  6. 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。

Read the full file on GitHub · 131 lines

Changes

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.

  1. 9d ago First seen · 131 lines · 29 tokens per session scan A d6e0360dd004

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories