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 agentscope-ai/skills --skill make_plan-engit clone --depth 1 https://github.com/agentscope-ai/skillsWrote 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/agentscope-ai/skills/make_plan-en)<a href="https://agentmods.dev/skills/agentscope-ai/skills/make_plan-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/skills/make_plan-en/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/agentscope-ai/skills/make_plan-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/skills/make_plan-en.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 | $0.00051 | $0.01511 |
| Opus 5.5 | $0.00020 | $0.00604 |
| Sonnet 5.5 | $0.00010 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
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 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.
This is a copy
100% identical to make_plan — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Plan
Use this Skill when you need to make an external plan request to a stronger Agent.
The goal of this Skill is not to outsource a task, but rather to:
- Request a plan from a stronger Agent
- The plan must consist of clear, actionable steps
- You execute the plan yourself
- Do not ask the consulted Agent to execute the task directly
How to invoke:
- Use
list_agents()to check available Agents - Use
chat_with_agent(...)to request the stronger Agent to "make a plan" - In
text, explicitly include the prompt: only provide a step-by-step executable plan, do not execute - To supplement or refine the original plan in a follow-up, pass
session_id
Recommended invocation skeleton:
list_agents()
chat_with_agent(
to_agent="<stronger_agent>",
text="[Agent <auto> requesting] Please help me create an execution plan for the following task. You do not need to execute the task -- just output clear, actionable steps in order.",
)
Core Rules
This Skill handles one thing only:
- Find a stronger Agent
- Request that Agent to output an execution plan
- Require the plan to be step-by-step, actionable, and in sequential order
- You execute the plan yourself rather than asking the other Agent to do it for you
If what you truly need is a "plan", use this Skill. If what you need is a final answer, architectural judgment, review conclusion, or direct execution, do not misuse this Skill.
Applicable Scenarios
The following scenarios are suitable for making an external plan request:
- The task requires multi-step decomposition
- Steps have dependencies between them
- A clear sequence, checkpoints, or verification points are needed
- Multiple modules, files, systems, or roles are involved
- The user explicitly requests a plan before execution
- You want to obtain a more complete and reliable execution path first
Do Not Use This Way
Do not use this Skill in the following situations:
- You actually want the other Agent to do the task for you
- What you really lack is a small piece of factual information, not a plan
- What you truly need is an architectural judgment or solution comparison
- You have not yet clearly understood the task objective
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.
- 1mo ago First seen · 198 lines · 51 tokens per session scan A 79b4c0b9d8e0
make_plan is a skill published in the GitHub repository agentscope-ai/skills (131 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,511 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to make_plan, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.