chat_with_agent

chat_with_agent is a skill for Claude Code, Codex from agentscope-ai/QwenPaw. It costs 30 tokens per session (1,284 once invoked), scanned A, original, Apache-2.0.

A procedure for asking another software agent for help, a review, a plan, or a second opinion. It explains how to find the right agent and continue an existing conversation.

In plain words
What is it for?
Use it when another agent's expertise is needed, when a user requests a specific agent, or when work should be delegated for background execution.
Why use it?
It prevents agents from being chosen by guesswork and keeps follow-up conversations connected to their earlier context. It also helps decide when another agent is unnecessary.

Skill for Claude CodeCodex

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

Good fit Use it when another agent's expertise is needed, when a user requests a specific agent, or when work should be delegated for background execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentscope-ai/qwenpaw/chat_with_agent-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 · 34,809 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 chat_with_agent-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 chat_with_agent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/chat_with_agent-zh"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/chat_with_agent-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,284 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 $0.00030 $0.01284
Opus 5 $0.00015 $0.00642
Sonnet 5 $0.00006 $0.00257
Haiku 4.5 $0.00003 $0.00128

Measured 13d ago against content hash 021f1f24b240, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

chat_with_agent 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 13d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

src/qwenpaw/agents/skills/chat_with_agent-zh/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

与 Agent 对话

什么时候用

当你需要向另一个 agent 询问问题、寻求帮助、请求方案、请求复核、请求决策支持,或者进行任何形式的交流时,使用本 skill。
如果用户明确要求与某个 agent 对话,也应使用本 skill。

应该使用

  • 需要另一个 agent 的专长、判断或第二意见
  • 需要向某个 agent 请求方案、复核或建议
  • 用户明确要求某个 agent 参与、协助或回答
  • 需要继续某个已有的 agent 会话,并保留上下文

不应使用

  • 你自己可以直接完成,且用户没有明确要求调用其他 agent
  • 只是普通问答,不需要专门 agent
  • 目标 agent 不明确,应该先追问或先查可用 agents
  • 刚收到某个 agent 的消息,又立刻回调同一个 agent,可能造成循环

决策规则

  1. 如果用户明确要求某个 agent,优先按要求执行,但仍要先查 agent,不要猜 ID
  2. 如果你自己能完成,就不要调用其他 agent
  3. 需要保留上下文续聊时,必须传 session_id
  4. 默认优先使用 list_agents()chat_with_agent(...) 进行前台对话,不要绕到别的方式
  5. 如果任务需要后台执行,使用 submit_to_agent(...) 提交,再用 check_agent_task(...) 查询状态

使用流程

请严格按照以下流程顺序使用本 skill:

  1. 确保你的工具列表中包含 list_agents()chat_with_agent(...) 两个内建工具
  • 这两个工具是与其他 agent 对话的基础,不要删除或禁用它们
  • 如果你没有这两个工具,请告诉用户你需要它们来与其他 agent 对话,并请求用户添加
  1. 使用 list_agents() 工具查看当前可用的 Agent,并从中选择一个 agent 提取其 id
  • 请根据用户的需求和对应 Agent 的描述来选择最合适的 Agent
  • 如果找不到合适的 Agent 且你不是 Default Agent,就使用 Default Agent
  • 否则告诉用户没有合适的 Agent 可用,并建议他们创建一个新的 Agent 或调整现有 Agent 的描述以便更好地匹配需求
  1. 调用 chat_with_agent(...) 发起前台求助,其中需要传递的关键参数包括
  • to_agent: 对话目标 Agent 的 ID,注意是 ID 不是名字
  • text: 你要对目标 Agent 说的内容
  • session_id: (可选)如果你需要与同一个 Agent 进行多轮对话,从第二轮开始传递相同的 session_id 来保持上下文连续
  • timeout: (可选)预估任务需要的前台等待时间,避免过早超时
  1. 如果任务适合后台执行,请使用新的后台工具路径
  • submit_to_agent(...):提交后台任务,需要 to_agenttext,以及可选的 session_id / task_timeout
    • 省略 task_timeout 时,默认执行预算为 3600 秒(1 小时)
    • 预计超过 1 小时的任务,请显式传入正数秒
    • 也接受数字字符串,例如 "7200"
  • check_agent_task(...):通过 task_id 查询任务状态,完成时返回最终结果
    • 超时后任务会以失败结束,错误类似 Task timed out after Ns(API 载荷中带 code=timeout

最小调用示例

新对话

list_agents()

chat_with_agent(
  to_agent="<target_agent_id>",
  text="[Agent <your_agent_id> requesting] 我需要你帮我判断这个问题的处理方向。",
)

续接已有对话

chat_with_agent(
  to_agent="<target_agent_id>",
  text="[Agent <your_agent_id> requesting] 请基于刚才的结论继续展开第 2 点。",
  session_id="<previous_session_id>",
)

Read the full file on GitHub · 123 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. 13d ago First seen · 123 lines · 30 tokens per session scan A 021f1f24b240

Subscribe to this mod's changes

chat_with_agent is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,809 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,284 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.