Skip to main content
subagent CX Codex

agent_autoname_receipt — Claude Code subagent: install

The agent_autoname_receipt Claude Code subagent reads existing name-confirmation cards and one coding agent’s current naming snapshot. It helps inspect the available evidence about a rename.

MIT ★ 395 updated 2026-11-16

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/agent_autoname_receipt.md
Open on GitHub

What agent_autoname_receipt does

The subagent reads existing agent_autoname confirmation cards and the current naming snapshot for one coding agent. Requests need the machine’s exact ID and the agent’s full session_id from agents_list.

The result cannot establish whether a specific model call started or finished. A snapshot may be older than the call or belong to another caller, so an ambiguous result is not a reason to retry. Optional since and before values must be supplied together as an RFC3339 window no longer than 24 hours. History is read in bounded pages, with incomplete pages reported.

It does not call the naming model, change settings, approve or resolve cards, rename agents, or publish session lists. It is not for Persona conversations, ordinary coding Agents, or extensions.

What it helps with

  • inspect an agent’s existing name-confirmation cards
  • read a coding agent’s current naming snapshot
  • check confirmation history within an RFC3339 time window
  • distinguish available evidence from proof that a model call completed

Example prompts for the agent

  • Inspect name-confirmation cards for machine MACHINE_ID and session FULL_SESSION_ID.
  • Read the naming snapshot for session FULL_SESSION_ID on machine MACHINE_ID.
  • Check confirmation history for FULL_SESSION_ID between since and before.

How to install agent_autoname_receipt

Manually: put the files in place

.claude/agents/agent_autoname_receipt.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about agent_autoname_receipt

How do I install agent_autoname_receipt in Claude Code?

Place the subagent file at .claude/agents/agent_autoname_receipt.md.

What does agent_autoname_receipt do?

It reads existing agent_autoname confirmation cards and one coding agent’s naming snapshot. It does not call the naming model or modify data.

What does agent_autoname_receipt need to run?

Provide the machine’s exact ID and the full session_id from agents_list. Optional since and before values are required together and define an RFC3339 window of up to 24 hours.

Source text

agent_autoname_receipt.md · MIT
Read-only: inspect the current assistant's existing agent_autoname confirmation cards and one coding agent's current naming snapshot. This does not prove that a particular earlier model call started, completed or succeeded: the model's tool-call id is not a manager-side correlation. The naming snapshot may predate the call or come from another caller, and background naming failures are not attributed to it. Do not retry a request from this result; unknown or ambiguous means the evidence cannot settle the outcome. Use only the exact machine and full session id from agents_list. The caller is verified from the actual assistant conversation; no other assistant's cards can be read. Optional since/before are an RFC3339 window of at most 24 hours, and must be supplied together. Confirmation history is read with bounded pages; incomplete pages are reported. This tool never calls the naming model, writes settings, approves or resolves a card, renames an agent, or publishes a session list. Not for Persona conversations, ordinary coding Agents, or extensions.

```json
{
  "type": "object",
  "additionalProperties": false,
  "required": ["machine", "session_id"],
  "properties": {
    "machine": {
      "type": "string",
      "description": "the machine's exact id, as agents_list shows it"
    },
    "session_id": {
      "type": "string",
      "description": "the agent's exact full session id, never a prefix"
    },
    "since": {
      "type": "string",
      "format": "date-time",
      "description": "inclusive RFC3339 start of the original confirmation window; requires before"
    },
    "before": {
      "type": "string",
      "format": "date-time",
      "description": "exclusive RFC3339 end of the original confirmation window [since,before); at most 24 hours after since"
    }
  }
}
```

© nwverse · MIT · nwverse/persona

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set61

The whole set →
agent_interrupt This Claude Code subagent stops another agent and can send it a new instruction immediately. Use it to interrupt a stalled loop, repeated failure, or work heading in the wrong direction. CX Codex ★ 395repo stars task_handoff The task_handoff Claude Code subagent sends part of an assigned task to a separate session through Persona. The handoff stays attached to the same to-do and supervisor. CX Codex ★ 395repo stars leader_progress The leader_progress Claude Code subagent adds direction updates to a work log. It reports completed goals and scheduled check-ins, rather than every intermediate step. CX Codex ★ 395repo stars interaction_answer The interaction_answer Claude Code subagent answers another agent’s question on the user’s behalf when the user has chosen an answer or delegated the choice. It picks from the offered options and leaves personal decisions to the user. CX Codex ★ 395repo stars ask_escalate The ask_escalate Claude Code subagent routes decisions that task agents cannot make to the user. It groups unanswered task questions into one reminder. CX Codex ★ 395repo stars agent_supervise The agent_supervise Claude Code subagent takes over an agent that was started without a task and tracks its work as a task in the current conversation. It routes progress messages to a supervisor and closes the task with task_review. CX Codex ★ 395repo stars task_decided The task_decided Claude Code subagent records an owner's answer to a pending task decision. It captures the choice when the owner gives it in the conversation. CX Codex ★ 395repo stars agents_list agents_list — a subagent for Claude Code and Codex monitoring running herdr sessions across user machines. Displays active jobs, pending approvals, and subscription limits. CX Codex ★ 395repo stars

Project sponsors

Companies that keep this analytics open