What is deepagents-planning-todos?

A guide for using task lists in Deep Agents, a framework for building AI agents. It explains how to split larger jobs into smaller tasks and track their progress.

Use it when designing workflows with three or more steps, user approvals, long-running tasks, or subtasks that need progress tracking.

It helps prevent multi-step work from becoming unclear or unfinished by making the plan and current progress explicit.

deepagents-planning-todos — Skill for Claude Code by soba-labs

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 soba-labs/langchain-agent-skills --skill deepagents-planning-todos

Clone the repo

git clone --depth 1 https://github.com/soba-labs/langchain-agent-skills

Made for: Claude Code.

Or install deepagents-skills, the plugin that ships this one along with the rest of its 3 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos/github.svg)](https://agentmods.dev/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos)

Your own site

<a href="https://agentmods.dev/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos"><img src="https://agentmods.dev/badge/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos"><img src="https://agentmods.dev/badge/skills/soba-labs/langchain-agent-skills/deepagents-planning-todos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,148 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 155
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.02148
Opus 5	$0.00054	$0.01074
Sonnet 5	$0.00022	$0.00430
Haiku 4.5	$0.00011	$0.00215

Measured 12d ago against content hash 8aaa7d5db9f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

deepagents-planning-todos 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/examples/todo-driven-agent/agent.py, scripts/visualize_todos.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/deepagents-planning-todos/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Agents Planning and Todos

Master the write_todos tool for effective task planning and decomposition in Deep Agents.

Use This Skill When

You need to break down complex multi-step tasks (3+ steps) into trackable subtasks.
You want to show users the plan before executing (user approval workflow).
You're debugging why todos aren't completing as expected.
You need patterns for different task types (research, coding, analysis, document processing).
You want to visualize todo progression from LangSmith traces.

When To Use write_todos

Use write_todos	Execute Directly
✅ Complex multi-step tasks (3-6 steps)	✅ Simple 1-2 step queries
✅ Tasks requiring user approval first	✅ Single tool calls
✅ Long-running workflows needing progress tracking	✅ Quick information lookups
✅ Tasks where planning adds clarity	✅ Straightforward API calls

Decision rule: If you'd benefit from showing the user "Here's my plan..." before starting, use write_todos.

Quick Start

from deepagents import create_deep_agent

# TodoListMiddleware is included by default in create_deep_agent
agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-5-20250929",
    tools=[search_tool, summarize_tool],
    system_prompt="You are a research assistant. Use write_todos for multi-step tasks."
)

# Agent workflow:
# 1. Call write_todos with initial plan
# 2. Ask user: "Does this plan look good?"
# 3. User approves → start executing
# 4. Update the todo list as work progresses
# 5. Keep todos aligned with the current plan and execution state

Example todo creation:

# Agent calls write_todos internally:
{
  "name": "write_todos",
  "arguments": {
    "todos": [
      {"content": "Search for papers on LLM agents", "status": "pending"},
      {"content": "Read and extract findings from top 5 papers", "status": "pending"},
      {"content": "Identify common themes", "status": "pending"},
      {"content": "Write summary report", "status": "pending"}
    ]
  }
}

Read the full file on GitHub · 248 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 248 lines · 108 tokens per session scan A 8aaa7d5db9f8

Subscribe to this mod's changes

deepagents-planning-todos is a skill published in the GitHub repository soba-labs/langchain-agent-skills (106 stars, last pushed 25d ago), licensed MIT. It adds 108 tokens to every session and 2,148 once invoked, about $0.0005 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.

Building agents Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens