Skip to main content
subagent CX Codex

task_continuation — Claude Code subagent for continuing tasks

The task_continuation subagent for Claude Code resumes work on an existing to-do. It keeps the original brief, decisions, and history on that task instead of opening a separate follow-up.

MIT ★ 395 updated 2026-11-16

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

What task_continuation does

task_continuation resumes the to-do identified by {{.TodoID}}. Earlier agents have been released, so the subagent continues the same task with its original brief, decisions, and history intact.

The continuation can be read-only or writable. In writable mode, it makes changes authorized by the current request while following the task’s other boundaries. To add it to Claude Code, place the file at .claude/agents/task_continuation.md.

What it helps with

  • resume an existing task after its earlier agents have been released
  • keep the original brief and decisions on the same to-do
  • make authorized changes without opening a separate follow-up task

Example prompts for the agent

  • Continue {{.TodoID}} and keep its brief, decisions, and history on the same to-do.
  • Resume the existing to-do {{.TodoID}} and make changes allowed by the current request.

How to install task_continuation

Manually: put the files in place

.claude/agents/task_continuation.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 task_continuation

How do I install task_continuation in Claude Code?

Place the agent file at .claude/agents/task_continuation.md.

What does task_continuation do?

It resumes an existing to-do after earlier agents have been released and keeps the task’s original brief, decisions, and history together.

Can task_continuation edit files?

The continuation can be read-only or writable. In writable mode, it makes changes authorized by the current request and keeps the task’s other boundaries.

Source text

task_continuation.md · MIT
Continue the existing to-do {{.TodoID}}. Its earlier Agents have been released; keep the original brief, decisions and history on this same to-do, rather than opening another one for follow-up work.
{{if .Readonly}}
This continuation is read-only.
{{else}}
This continuation is writable. The earlier Agent's read-only execution restriction does not apply to this replacement Agent. Make the changes authorized by the current request; all other task boundaries still apply.
{{end}}

© nwverse · MIT · nwverse/persona

Similar subagents

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

From the same set61

The whole set →
answer This Claude Code prompt answers questions using material from a recorded meeting. If no question was typed, it picks the latest spoken question addressed to Persona or the meeting owner. GP ChatGPT ★ 395repo stars room_claude The room_claude prompt for Claude Code sets up an assistant for a recorded meeting. It tracks topics and key points, answers from meeting material, and handles photos sent during the meeting. GP ChatGPT ★ 395repo stars instructions The instructions prompt for Claude Code and ChatGPT sets rules for Persona’s voice assistant. It routes requests to the right conversation and guides when to answer, search, or hand off work. GP ChatGPT ★ 395repo stars supervision_instructions supervision_instructions is a Claude Code prompt for supervising agent tasks and checking their results. It defines how to track assignments, respond to status signals, and decide whether work is ready to accept. GP ChatGPT ★ 395repo stars agent_unarchive The agent_unarchive Claude Code subagent returns an archived coding-agent session to the Agents list. It also asks the agent’s own tool to restore the session where it was archived. CX Codex ★ 395repo stars task_start_screen The task_start_screen Claude Code subagent reads the last lines of a task’s terminal tab when its agent failed to start. It shows a shell prompt waiting for input or the point where the agent’s screen stopped. CX Codex ★ 395repo stars dispatch_task The dispatch_task Claude Code subagent takes work from another coding agent and handles it itself. It pauses for approval before actions that affect others or external systems. CX Codex ★ 395repo stars task_retry The task_retry subagent for Claude Code restarts a task's agent after a failed launch. It reuses the existing tab when possible, or opens a new one. CX Codex ★ 395repo stars

Project sponsors

Companies that keep this analytics open