agent_send — Claude Code subagent for messaging agents
This Claude Code subagent sends messages to another agent and can assign it supervised work. It can resume a stopped agent with its context when the recorded stop reason allows it.
MIT ★ 395 updated 2026-11-16
.claude/agents/agent_send.mdWhat agent_send does
agent_send sends an agent a message phrased as a user request; if the agent is busy, the message waits in a queue. New work can be sent with completion criteria so the agent has a supervised task. Replies, nudges and decisions can be sent without creating a task.
Resuming is allowed only after a recorded stop for idleness, task completion or restart. A user-initiated or unknown stop requires the user's approval. For unrelated work, nearly full context or an agent that has gone off track, start a new agent and read the old one. Install for Claude Code with .claude/agents/agent_send.md.
What it helps with
- queue a message for a busy agent
- assign supervised work with completion criteria
- continue related work using an agent's prior context
- start a new agent for unrelated work
Example prompts for the agent
- Ask the agent to check error handling and report when the tests are ready.
- Send the agent a clarification about its current task without creating another task.
- Continue with the previous agent's context and fix the issue found during the investigation.
How to install agent_send
Manually: put the files in place
.claude/agents/agent_send.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/agent_send.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/agent_send.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about agent_send
How do I install agent_send in Claude Code?
Add .claude/agents/agent_send.md to the project.
What does agent_send do?
It sends messages to agents, queues them while an agent is busy, and can assign new work with completion criteria. Related work can continue in the previous context when the stop reason permits a resume.
When can agent_send resume a stopped agent?
Only after a recorded stop for idleness, task completion or restart. A user-initiated or unknown stop requires the user's approval.
Source text
agent_send.md · MIT
Send a message to an agent as the user would type it; queued while it works. Only send what the user asked for. A stopped agent takes no plain message. Only a recorded non-user stop (idle, task completion, restart) permits resume; user and unknown stops need the user's Resume. If the next work needs its context (investigation followed by a fix, rework, the user asked for this agent), send with resume and resume_why: the same session and permission mode, your text first, the reason shown to the user. It must be supervised (give task unless it is on an open task of yours). Unrelated work, a nearly full context or an agent gone off track: agent_start a new one (agent_read the old one). Unsure: ask_user, reuse or new. A failed resume says why. A user's branch that never ran is started by its first message. Only /exit or /quit stops a running agent (tab kept); finished tasks' agents stop automatically. /exit to another conversation's task is refused (the user can close it, or agent_archive with close).
A dialog holding its terminal refuses the send (dialog_open) with its first line and whether Enter alone closes it; then send with dismiss_notice true. Confirmations, permissions and pickers are never closed for you: tell the user, or use interaction_answer.
To hand new work to a running agent (one the user opened, a long-lived one that passes work on), give task from the main conversation: once sent, the agent is your supervised task as agent_supervise makes one (a todo with the text as notes, done_when, a card; 督办 messages, task_review). Put the criteria in the text too: the agent reads only the text. An agent on one of your tasks takes more under the same title (done_when updated); another title, the user's own todo or another conversation's task is refused, with nothing sent. A failed send makes no task. Leave task out or null for a reply, nudge or decision; a task with only blank fields counts as left out.
```json
{
"type": "object",
"required": ["machine", "session_id", "text"],
"properties": {
"machine": {
"type": "string"
},
"session_id": {
"type": "string"
},
"text": {
"type": "string"
},
"resume": {
"type": "boolean",
"description": "resume this stopped agent with its context, text as its first message"
},
"resume_why": {
"type": "string",
"description": "why its context is needed (shown to the user)"
},
"dismiss_notice": {
"type": "boolean",
"description": "Press Enter first to close a notice that only says \"Enter to continue\" (no options). Any other dialog still refuses the send."
},
"attachments": {
"type": "array",
"maxItems": 8,
"items": { "type": "string" },
"description": "pictures and files the user gave you for it, by their absolute paths on your computer: a picture they sent (the path Claude Code gives it), a file the app put in their message. They are copied to the agent's computer and listed at the end of its message, and the text's mentions of them name the copies. Only those the user gave you in this conversation are accepted"
},
"task": {
"type": ["object", "null"],
"description": "new work: make it your supervised task first (main conversation only); null for a reply",
"additionalProperties": false,
"properties": {
"title": {
"type": "string",
"description": "the task in a short line (Chinese, under 20 characters)"
},
"done_when": {
"type": "array",
"maxItems": 6,
"items": { "type": "string" },
"description": "results you can check when it says it is done (a PR merged, a sheet's link, what the live system answers)"
},
"expect_minutes": {
"type": "integer",
"description": "how long it should take from now; longer without progress counts as stuck"
}
}
}
}
}
```
© nwverse · MIT · nwverse/persona