chat_with_agent

chat_with_agent is a skill for Claude Code, Codex from mateaix/mateclaw. It costs 39 tokens per session (813 once invoked), scanned A, original, Apache-2.0.

A procedure for asking another available coding agent for advice, a review, or help with a separate task. It supports one request or up to three independent requests at the same time.

In plain words
What is it for?
Use it to find available agents, delegate a question or review, or split independent research and analysis tasks across agents.
Why use it?
It provides a way to obtain another agent's specialist judgment when a second opinion or parallel work would help.

Skill for Claude CodeCodex

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/mateaix/mateclaw/chat_with_agent
Any agent
npx skills add mateaix/mateclaw --skill chat_with_agent
Clone the repo
git clone --depth 1 https://github.com/mateaix/mateclaw

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/mateaix/mateclaw/chat_with_agent.svg)](https://agentmods.dev/skills/mateaix/mateclaw/chat_with_agent)
Your own site
<a href="https://agentmods.dev/skills/mateaix/mateclaw/chat_with_agent"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/chat_with_agent.svg" alt="Measured on agentmods" 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 813 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 $0.00039 $0.00813
Opus 5 $0.00019 $0.00407
Sonnet 5 $0.00008 $0.00163
Haiku 4.5 $0.00004 $0.00081

Measured 4d ago against content hash 31b842280add, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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

5 near-identical copies found in the catalogue:

mateclaw-server/src/main/resources/skills/chat_with_agent/SKILL.md · 88 lines

What it actually says

与 Agent 对话

何时使用

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,或用户明确要求某个 Agent 参与时使用。

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 参与或协助
  • 多个独立子任务需要并行分配给不同 Agent

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
  • 刚收到某个 Agent 的消息,不要立刻回调同一个 Agent(防止死循环)

工作流程

第一步:查询可用 Agent

listAvailableAgents()

返回所有已启用 Agent 的名称、类型和描述,根据描述选择最合适的 Agent。

第二步A:单次委托(串行)

delegateToAgent(
  agentName="data-analyst",
  task="[来自 Agent my-agent 的请求] 请帮我分析以下销售数据,给出环比趋势摘要:..."
)
  • agentName:目标 Agent 的名称(从 listAvailableAgents() 返回值中取)
  • task:发送给目标 Agent 的完整任务描述
  • 建议在 task 开头加 [来自 Agent <自身名称> 的请求] 便于对方识别来源

第二步B:并行委托(多个独立任务同时进行)

最多同时委托 3 个 Agent:

delegateParallel(
  tasksJson="[
    {\"agentName\": \"research-agent\", \"task\": \"[来自 Agent coordinator 的请求] 搜索 AI 行业最新融资动态\"},
    {\"agentName\": \"data-analyst\", \"task\": \"[来自 Agent coordinator 的请求] 分析上季度销售数据趋势\"}
  ]"
)

tasksJson 是 JSON 数组字符串,每个元素包含 agentNametask

决策规则

  1. 用户明确要求调用某 Agent → 先 listAvailableAgents() 确认名称,不要猜
  2. 能自己完成 → 不调用
  3. 多个互相独立的子任务 → 用 delegateParallel,不要串行逐个调用
  4. 不超过 3 个并行 → 超过时按优先级分批
  5. 收到 Agent B 回复后 → 不要立刻回调 Agent B

与 make_plan 的区别

技能 用途
chat_with_agent 向 Agent 咨询、委托、获取结果
make_plan 专门向更强 Agent 索要执行计划(由自己执行)

注意事项

  • delegateToAgent 是同步阻塞调用,等待目标 Agent 完成后返回结果
  • delegateParallel 并发执行,等所有任务完成后一次性返回所有结果
  • MateClaw 当前不支持跨调用的会话 session 续接,每次 delegateToAgent 是独立对话
  • 如需上下文连贯,在 task 参数中附带上一次的关键结论
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. 4d ago First seen · 88 lines · 39 tokens per session scan A 31b842280add

Subscribe to this mod's changes

chat_with_agent is a skill published in the GitHub repository mateaix/mateclaw (1,061 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 813 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.

Related

Other skills, from other repositories

make-skill

Use this skill when sedimenting a session into a reusable workspace skill. Triggers when the user wants to turn the current conversation, workflow, or troubleshooting path into a SKILL.md. Phrases like 'turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this', and any /make-skill…

agentscope-ai/QwenPaw · 85 tokens

make-skill

用于把当前会话沉淀为可复用的 workspace skill。当用户希望把当前对话、工作流或排错路径写成 SKILL.md 时触发。触发表达包括「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」以及任何 /make-skill 调用。.

agentscope-ai/QwenPaw · 84 tokens

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…

agentscope-ai/QwenPaw · 62 tokens

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

agentscope-ai/QwenPaw · 168 tokens

docx

当用户需要创建、读取、编辑或处理 Word 文档(.docx)时,使用此技能。触发场景包括提到“Word 文档”、“.docx”,或要求生成带目录、标题、页码、信头等格式的专业文档;也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注,以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物,也应使用此技能。不要用于 PDF、电子表格、Google Docs,或与文档生成无关的一般编程任务。.

agentscope-ai/QwenPaw · 161 tokens

multi_agent_collaboration

Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use qwenpaw agents chat for two-way communication with replies.

agentscope-ai/QwenPaw · 47 tokens