make_plan

make_plan is a skill for Claude Code, Codex from agentscope-ai/QwenPaw. It costs 39 tokens per session (1,467 once invoked), scanned A, original, Apache-2.0.

A guide for requesting a clear, ordered work plan from a stronger coding agent without asking that agent to do the work.

In plain words
What is it for?
Use it to ask for a plan, refine it through the same conversation, and follow the resulting steps yourself.
Why use it?
It helps break a multi-step task into actions, dependencies, checks, and completion criteria before implementation begins.

Skill for Claude CodeCodex

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

Good fit Use it to ask for a plan, refine it through the same conversation, and follow the resulting steps yourself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentscope-ai/qwenpaw/make_plan-zh
About the project

QwenPaw is a personal AI assistant that runs on a local machine or in the cloud and connects to multiple chat applications. It provides memory, file workspaces, multiple agents, skills, plugins, and integrations with language-model providers and external tools. The catalogue entries are skills that extend its capabilities.

agentscope-ai/QwenPaw · 35,089 stars · on GitHub · qwenpaw.agentscope.io

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 agentscope-ai/QwenPaw --skill make_plan-zh
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/QwenPaw

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 make_plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/make_plan-zh/github.svg)](https://agentmods.dev/skills/agentscope-ai/qwenpaw/make_plan-zh)
Your own site
<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/make_plan-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/make_plan-zh/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 make_plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/make_plan-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/make_plan-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,467 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. ✓ AI security review Fable 5.1 · 6 Sept 2026 📄 Read the review Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00039 $0.01467
Opus 5 $0.00019 $0.00733
Sonnet 5 $0.00008 $0.00293
Haiku 4.5 $0.00004 $0.00147

Measured 10d ago against content hash f03e62e7c3e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

make_plan 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 10d 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.

src/qwenpaw/agents/skills/make_plan-zh/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

制定计划

当你需要向更强 Agent 发起一次外部计划请求时,使用本 Skill。

本 Skill 的目标不是把任务外包出去,而是:

  • 向更强 Agent 要一份计划
  • 这份计划必须是明确的执行步骤
  • 由你自己按计划执行
  • 不要求被求助的 Agent 直接动手执行任务

调用步骤:

  1. 使用 list_agents() 查可用 Agent 的 ID
  • 可根据返回的描述信息选择最合适的 Agent 来求助
  • 如果找不到非常合适的 Agent,就选择 default
  • 注意区分 Agent 的 ID 和 Name,后续调用需要的是 ID
  1. 使用 chat_with_agent(...) 向更强 Agent 请求“制定计划”
  • to_agent 传目标 Agent ID
  • text 中明确给出提示仅需给出可按步骤执行的计划,不要执行
  1. 收到回复后,记录对话的 session_id,并提炼出真正可执行的步骤,并由你自己执行
  • 如果有不清楚的地方可以继续追问细化计划,但仍然要强调只补计划,不要代执行
  • 追问仍使用 chat_with_agent(...),并传入记录的 session_id 以保持上下文

推荐调用骨架:

list_agents()

chat_with_agent(
  to_agent="stronger_agent",
  text="[Agent <auto> requesting] 请帮我为下面任务制定执行计划。你不需要执行任务,只需要输出明确、可落地、按顺序排列的步骤。",
)

适用场景

以下场景适合直接发起外部计划请求:

  • 任务需要多步拆解
  • 步骤之间有依赖关系
  • 需要明确先后顺序、检查点或验证点
  • 涉及多个模块、文件、系统或角色
  • 用户明确要求先给出计划
  • 你希望先拿到一份更完整、更稳妥的执行路径

不要这样用

以下情况不要用本 Skill:

  • 你其实是想让对方直接替你做任务
  • 真正缺的是一个小事实,而不是计划
  • 真正需要的是架构判断或方案比较
  • 你连任务目标都没理解清楚

向更强 Agent 要什么

调用 chat_with_agent(...) 时要明确说明:

  • 你需要的是计划,不是代执行
  • 步骤必须具体,不能只给抽象建议
  • 最好包含验证方式与完成标志

求助模板

请帮我为下面任务制定一份执行计划。 你不需要执行任务本身,只需要输出计划。

任务: [要做什么]

目标: [最终想达到什么结果]

约束:

  • [...]
  • [...]

计划要求:

  1. 拆成明确、可执行的步骤
  2. 标明推荐顺序
  3. 必要时指出依赖、检查点或验证方式
  4. 如果有明显风险,补充关键注意点

输出格式: [例如:输出 5-8 个编号步骤,每步 1-3 句]

chat_with_agent 请求示例:

chat_with_agent(
  to_agent="strong_agent",
  text="""
请帮我为下面任务制定一份执行计划。
你不需要执行任务本身,只需要输出计划。

任务:
修改一个多模块功能。

目标:
以较低风险完成改动,并避免遗漏联动点。

约束:
- 尽量减少返工
- 需要保留可验证的中间检查点

计划要求:
1. 拆成可落地的步骤
2. 标明推荐顺序
3. 标出关键依赖和检查点
4. 尽量包含验证方式

输出格式:
请输出 3-5 个编号步骤,每步尽量具体。
""",
)

chat_with_agent 回复示例:

[SESSION: xxx]

下面是我为你制定的执行计划:

1. ...
2. ...
  • 其中 xxx 是本次对话的 session_id,你需要记录下来以便后续追问细化,一般是一个较长的字符串,例如 local_agent:to:strong_agent:1776406127168:e11b08d8

chat_with_agent 追问示例(假设你想让对方细化第 3 步):

chat_with_agent(
  to_agent="strong_agent",
  text="请基于刚才的计划,再细化第 3 步。仍然只需要补计划,不需要代执行任务。",
  session_id="xxx",
)

收到计划后怎么用

把更强 Agent 的回复当作“执行计划输入”,不是“任务已经完成”。

你应该做的是:

  1. 提炼出真正可执行的步骤
  2. 判断是否需要按你的环境做微调
  3. 由你自己执行这些步骤
  4. 遇到新不确定性时,再继续细化计划

Read the full file on GitHub · 185 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. 10d ago First seen · 185 lines · 39 tokens per session scan A f03e62e7c3e6

Subscribe to this mod's changes

make_plan is a skill published in the GitHub repository agentscope-ai/QwenPaw (35,089 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,467 once invoked, about $0.0002 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.