task-planning

task-planning is a skill for Claude Code, Codex from adamancyzhang/claude-orchestrator-server. It costs 111 tokens per session (1,915 once invoked), scanned A, original, MIT.

A planning method for turning requirements into an ordered set of executable tasks with acceptance criteria, ownership, and traceability.

In plain words
What is it for?
Use it to analyse requirements, define a task blueprint, break work into tasks, set verification rules, and send tasks to an orchestrator queue.
Why use it?
It replaces vague work requests with a documented plan that can be checked and handed to implementers.

Skill for Claude CodeCodex

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

Good fit Use it to analyse requirements, define a task blueprint, break work into tasks, set verification rules, and send tasks to an orchestrator queue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamancyzhang/claude-orchestrator-server/task-planning
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 adamancyzhang/claude-orchestrator-server --skill task-planning
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-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-planning/github.svg)](https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-planning)
Your own site
<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-planning"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-planning/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 task-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-planning"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,915 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 $0.00111 $0.01915
Opus 5.5 $0.00044 $0.00766
Sonnet 5.5 $0.00022 $0.00383
Haiku 4.5 $0.00011 $0.00192

Measured 1mo ago against content hash 7546f448e7f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-planning 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 1mo 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-planning/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Planning

规划不是猜测,是分析需求 → 定义蓝图 → 拆解可执行任务 → 建立可验证的验收标准。本技能与 [[task-traceability]] 协作,确保每次规划产出清晰、可执行、可追溯——每个任务都可追溯到具体需求。


何时触发

  • Leader 分配新的需求/目标给 Planner
  • 用户说"分析一下这个需求"、"拆解任务"、"制定执行计划"
  • 新的工作周期开始,需要产出任务列表
  • 现有蓝图需要修订或补充

规划六步法

按顺序执行,每一步通过才进入下一步。任一步产出不清晰 → 回退澄清。

1. 读取需求上下文

定位并理解需求来源:

  • 如果是 Leader 通过 orchestrator 分配的需求,通过 claude-orchestrator get-context --key <需求key> 获取
  • 如果是本地文档(如 docs/pm/YYYY-MM-DD/),读取完整内容
  • 如果是代码库需求(如 Issue、PR 描述),读取相关文档和代码

提取关键信息:

  • 业务目标和背景
  • 约束条件和边界
  • 期望的交付标准和截止时间

2. 定义任务蓝图

输出蓝图文档,包含以下要素:

# 任务蓝图:[目标名称]

> Planner | YYYY-MM-DD | 版本 v1

## 目标

(一句话描述要达成什么)

## 背景

(为什么需要做这个,解决什么问题)

## 范围与非范围

**范围内:**
- 具体要做的事项 1
- 具体要做的事项 2

**不在范围内:**
- 明确不做的事项 1

## 约束条件

- 技术约束(如必须兼容 Node.js 18+)
- 时间约束
- 依赖约束(如依赖外部服务 X 先就绪)

## 成功定义

(可验证的成功标准,不是抽象描述)
- 标准 1:所有单元测试通过,覆盖率 ≥ X%
- 标准 2:UI 交互流程可在浏览器中完成
- ...

3. 拆解可执行任务

将蓝图拆解为独立的任务项。每个任务必须满足:

  • 可独立执行:Builder 无需频繁跨任务上下文切换
  • 可验证:有明确的验收标准(测试命令、UI 检查点、文件路径等)
  • 有产出物:代码变更、测试报告、截图、文档等
## 任务清单

| # | 任务 | 类型 | 验收标准 | 预估 | 依赖 |
|---|------|------|---------|------|------|
| 1 | 实现 XXX 模块 | build | `npm test -- XXX` 全部通过 | 2h | - |
| 2 | 编写 YYY 集成测试 | build | `npm test -- YYY` 覆盖 3 个场景 | 1h | #1 |
| 3 | 验证 ZZZ 边界情况 | verify | 运行边界测试套件,0 失败 | 0.5h | #2 |
| 4 | 审查整体方案一致性 | review | 审查报告无 P0/P1 问题 | 0.5h | #2, #3 |
| 5 | 验收最终交付物 | accept | 对照验收标准逐项通过 | 0.5h | #4 |

任务类型对应责任链环节:plan / build / verify / review / accept。

依赖字段确保责任链顺序:P → B → V → R → A。

4. 推入任务队列

通过 orchestrator 将任务推入队列,指定每个任务的责任链环节:

# Build 任务
claude-orchestrator push-task \
  --title "实现 XXX 模块" \
  --link build \
  --priority 0

# Verify 任务
claude-orchestrator push-task \
  --title "验证 ZZZ 边界情况" \
  --link verify \
  --priority 1

# Review 任务
claude-orchestrator push-task \
  --title "审查整体方案一致性" \
  --link review \
  --priority 1

# Accept 任务
claude-orchestrator push-task \
  --title "验收最终交付物" \
  --link accept \
  --priority 1

优先级建议:plan 和下游瓶颈任务用 0(HIGH),其余用 1(MEDIUM)。

Read the full file on GitHub · 189 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. 1mo ago First seen · 189 lines · 111 tokens per session scan A 7546f448e7f8

Subscribe to this mod's changes

task-planning is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 7d ago), licensed MIT. It adds 111 tokens to every session and 1,915 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-11.