import-plan

A command that turns a Claude Code plan file into individual tasks in the built-in task list. Claude Code is a coding assistant, and the command also archives the original plan inside the project.

In plain words
What is it for?
Use it to import a plan from a specified file, a plan remembered from the conversation, or the most recently changed plan in Claude's plans folder.
Why use it?
It removes the need to copy plan steps into tasks by hand and keeps a dated copy of the plan with the project.

Command

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 commands/motlin/claude-code-plugins/import-plan
Clone the repo
git clone --depth 1 https://github.com/motlin/claude-code-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 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 $0.00011 $0.00853
Opus 5 $0.00005 $0.00426
Sonnet 5 $0.00002 $0.00171
Haiku 4.5 $0.00001 $0.00085

Measured 2d ago against content hash 345ae7b38597, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import-plan 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 2d 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.

plugins/builtin-tasks/commands/import-plan.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Import Plan

Convert a structured plan file from Claude Code's plan mode into individual tasks using TaskCreate, where each task references a specific step in the archived plan.

Locate the Plan File

  • If $ARGUMENTS is provided, use it as the plan file path.
  • Otherwise, use the plan file you remember writing or editing earlier in this conversation.
  • If no plan was written in this conversation, pick the most recently modified .md file in ~/.claude/plans/, then confirm with the user via AskUserQuestion that it's the right plan — concurrent Claude sessions may be writing other plans into the same directory.
  • If ~/.claude/plans/ has no .md files, tell the user and stop.

Read the plan file to understand its structure and steps.

Archive the Plan Locally

  1. Create the .llm/plans/ directory if it does not exist
  2. Choose a concise, descriptive name based on the plan content (e.g., add-import-plan-command)
  3. Move the file: ~/.claude/plans/<original-name>.md.llm/plans/<yyyy-mm-dd>-<descriptive-name>.md
  4. Record the absolute path to the archived file for use in tasks

Create Tasks

For each step in the plan, create a task using TaskCreate with:

  • subject: A brief imperative description of the step (e.g., "Add validation to user input handler")
  • activeForm: Present continuous form for spinner text (e.g., "Adding validation to user input handler")
  • description: Full standalone context including all fields below

Each task's description must include:

  1. A brief description of what the step accomplishes
  2. An instruction line: Read and follow step N from the plan at \``
  3. Key file paths and identifiers mentioned in that step (for standalone context)

Standalone Context

Each task is executed in isolation by an agent that can only see one task at a time via TaskGet. Therefore:

  1. Every task must contain ALL context needed to implement it
  2. Repeat shared context in every related task — if 5 tasks share the same background, repeat it 5 times
  3. Never reference other tasks — phrases like "similar to task above" are useless
  4. Include the full picture — source of inspiration, files involved, patterns to follow
  5. Use full absolute paths, exact class/function names, and specific implementation details

Read the full file on GitHub · 76 lines

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. 2d ago First seen · 76 lines · 11 tokens per session scan A 345ae7b38597

Subscribe to this mod's changes

import-plan is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 11 tokens to every session and 853 once invoked, about $0.0001 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.