task-execution

task-execution is a skill for Claude Code, Codex from adamancyzhang/claude-orchestrator-server. It costs 116 tokens per session (1,498 once invoked), scanned A, original, MIT.

A step-by-step guide for carrying out a coding task from its plan through implementation, testing, and reporting. It is designed for an Executor working in a coordinated team of coding agents.

In plain words
What is it for?
Use it to claim a planned task, read its requirements, make the scoped code changes, run acceptance checks, and report the outputs and commit details.
Why use it?
It reduces guesswork about what to change and how to check the result. It also records why each code change was made and whether the required checks passed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/adamancyzhang/claude-orchestrator-server/task-execution
Any agent
npx skills add adamancyzhang/claude-orchestrator-server --skill task-execution
Clone the repo
git clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-server

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 task-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-execution.svg)](https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-execution)
Your own site
<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-execution"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00116 $0.01498
Opus 5 $0.00058 $0.00749
Sonnet 5 $0.00023 $0.00300
Haiku 4.5 $0.00012 $0.00150

Measured 6d ago against content hash c254c279432e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

task-execution 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 6d 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.

skills/task-execution/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Execution

执行不是凭感觉写代码,是理解蓝图 → 精准实现 → 自证正确 → 记录可追溯的完整闭环。本技能与 [[task-traceability]] 协作,确保 Executor 的每次执行产出可被 Verifier 独立验证,每个代码变更都可追溯到具体的 Plan 要求。


何时触发

  • Worker 通过 claude-orchestrator claim-task 认领了 execute 类型的任务
  • 用户说"开始执行"、"开始构建"、"implement this task"
  • Leader 直接分配了 execute 任务给 Executor
  • 任务蓝图中标记为 execute 的项需要开工

执行六步法

按顺序执行,每一步通过才进入下一步。

1. 认领任务并获取上下文

# 认领任务
claude-orchestrator claim-task

# 获取蓝图
claude-orchestrator get-context --key plan-<目标slug>

从任务和蓝图中提取:

  • 本任务的验收标准(具体到命令和文件路径)
  • 前序依赖任务的产出物(Plan 的输出、上游 Execute 的产出)
  • 本任务的预期产出物

如果蓝图不在共享上下文中,通过消息向 Planner 索要。

2. 理解执行范围

通读蓝图中的相关部分,确认理解无误:

  • 明确"做什么"和"不做什么"——不要在实现中越界
  • 识别与上游产出物的接口(API 契约、文件协议等)
  • 确认验收标准的可复现性——如果你无法按验收标准自测,验收标准本身有缺陷,反馈给 Planner

如果蓝图有歧义或不清晰 → 通过消息联系 Planner 澄清,不要猜测。

3. 执行实现

按照蓝图执行代码变更:

  • 只做任务范围内的事,不顺手重构无关代码
  • 遵循项目现有的代码规范和架构模式
  • 编写必要的测试(如果验收标准要求)
  • 产出物(测试报告、截图等)放入约定的输出路径

与 [[task-traceability]] 协作:每次代码提交遵循可追溯工作流——自己的名字签名、commit hash 记录回任务文档。

4. 自测验证

在报告完成之前,自行运行验收标准中的验证命令:

# 示例:运行测试
npm test -- <test-pattern> 2>&1

# 示例:检查产出物
ls -la <expected-output-path>

如果验收标准中定义了多个检查点,逐项执行并记录结果。所有检查点通过后才进入下一步。

如果某项检查失败但属于外部原因(非本任务引入的问题),在报告中标注为已知问题,不阻塞完成。

5. 提交代码

按照 [[task-traceability]] Step 3-5 完成提交链:

# Step 3: 提交代码(用自己的名字签名)
git add <changed-files>
git commit -m "feat(<scope>): <description>

<details>

<Your Name>"

# Step 4: 记录 commit hash 到任务文档
# Step 5: 提交文档更新

关键规则:

  • 一个逻辑单元一个 commit,不批量提交不相关的变更
  • commit message 末尾签自己的名字
  • 记录 commit hash 回任务文档

6. 报告完成

标记任务完成并通知:

claude-orchestrator complete-task \
  --task-id <task-id> \
  --result "完成了 XXX,commit: a1b2c3d。测试全部通过。产出物: <path>"

执行完成检查清单

□ 已认领任务并从蓝图获取上下文
□ 已理解执行范围和验收标准
□ 代码变更只在任务范围内,无越界修改
□ 验收标准中的命令自测全部通过
□ 代码已提交,签名为自己的名字 (task-traceability Step 3)
□ commit hash 已记录回任务文档 (task-traceability Step 4)
□ 任务文档更新已提交 (task-traceability Step 5)
□ 已通过 orchestrator complete-task 报告完成

与其他技能的协作

  • [[task-traceability]]:基础层。Executor 严格遵循追溯 → 执行 → 映射 → 举证 → 记录的五步法。每个代码变更必须追溯至 Plan 的具体要求,映射到实现,附带测试证据,并通过 commit hash 记录回任务文档。
  • [[task-planning]]:Executor 依赖 Planner 的蓝图和追溯链来理解执行范围。如果蓝图有歧义,反馈给 Planner 澄清。
  • [[task-verification]]:Verifier 将独立验证 Executor 的产出。Executor 的自测和可追溯记录降低了 Verifier 发现基础问题的概率。

Read the full file on GitHub · 143 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. 6d ago First seen · 143 lines · 116 tokens per session scan A c254c279432e

Subscribe to this mod's changes

task-execution is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,498 once invoked, about $0.0006 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

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens