subdivide

subdivide is a skill for Claude Code from sanghyun-io/plan-subdivider. It costs 23 tokens per session (2,551 once invoked), scanned A, original, MIT.

A planning tool that breaks one detailed plan file into separate task files.

In plain words
What is it for?
Use it after creating a detailed plan to split the plan into individual implementation tasks.
Why use it?
It turns a large plan into smaller pieces that are easier to work through and track.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the ExitPlanMode tool.

Part of the plan-subdivider plugin — 1 skill, 1 hook shipped together

Good fit Use it after creating a detailed plan to split the plan into individual implementation tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sanghyun-io/plan-subdivider/plan-subdivide
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 sanghyun-io/plan-subdivider --skill plan-subdivide
Clone the repo
git clone --depth 1 https://github.com/sanghyun-io/plan-subdivider

Made for: Claude Code.

Or install plan-subdivider, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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.

agentmods badge for subdivide

README.md
[![agentmods](https://agentmods.dev/badge/skills/sanghyun-io/plan-subdivider/plan-subdivide/github.svg)](https://agentmods.dev/skills/sanghyun-io/plan-subdivider/plan-subdivide)
Your own site
<a href="https://agentmods.dev/skills/sanghyun-io/plan-subdivider/plan-subdivide"><img src="https://agentmods.dev/badge/skills/sanghyun-io/plan-subdivider/plan-subdivide/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.

agentmods 80×15 button for subdivide

Your own site · 80×15
<a href="https://agentmods.dev/skills/sanghyun-io/plan-subdivider/plan-subdivide"><img src="https://agentmods.dev/badge/skills/sanghyun-io/plan-subdivider/plan-subdivide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,551 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.
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 5.1 $0.00023 $0.02551
Opus 5 $0.00012 $0.01275
Sonnet 5 $0.00005 $0.00510
Haiku 4.5 $0.00002 $0.00255

Measured 8d ago against content hash aab7e3647044, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

subdivide 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 8d 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.

skills/plan-subdivide/SKILL.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Subdivide Skill

A skill that breaks down an existing plan file into detailed task files.


⚠️ Plan Mode Check (Top Priority)

IMPORTANT: If you are in Plan mode, exit it first before running this skill.

Behavior When Plan Mode is Detected

  1. Run ExitPlanMode: Exit Plan mode first
  2. Then run /subdivide normally: Proceed from Step 1 after exiting

Why Is Exiting Plan Mode Necessary?

  • In Plan mode, file creation (Write) is interpreted as a plan file
  • During plan analysis, the system attempts to write a new plan
  • After exiting Plan mode, subdivision work can proceed normally

Usage

/subdivide                           # Subdivide the most recent plan file
/subdivide ~/.claude/plans/my-plan.md  # Subdivide a specific plan file

Execution Steps

Step 0: Exit Plan Mode

  1. Check if currently in Plan mode
  2. If in Plan mode, run ExitPlanMode to exit
  3. After exiting, proceed to Step 1

Step 1: Locate Plan File

  1. If a path is provided as an argument, use that file
  2. Search the current conversation context for the Plan file:
    • If the context contains Plan content (plan title, file path, etc.), use that file
    • If immediately after ExitPlanMode, prioritize the plan file just created
    • If the Plan filename cannot be extracted from context, proceed to next step
  3. If neither of the above applies, select the most recently modified .md file from ~/.claude/plans/
  4. If the plan is already subdivided (folder exists), warn and request confirmation

Step 2: Analyze Plan

Read the plan file and extract:

  1. Overall objective: The main purpose of the plan
  2. Task list: Tasks to be performed
  3. Dependencies: Order/dependencies between tasks
  4. Reference sections: Section numbers in the original plan

Analysis criteria (Rules reference: @~/.claude/rules/plan-structure.md):

  • Separate by independent deliverable units
  • Consider logical ordering
  • Compose into verifiable units

Read the full file on GitHub · 407 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. 8d ago First seen · 407 lines · 23 tokens per session scan A aab7e3647044

Subscribe to this mod's changes

subdivide is a skill published in the GitHub repository sanghyun-io/plan-subdivider (2 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 2,551 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 2026-08-31.

Related

Other skills, from other repositories

chief-revenue-officer

Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…

cbrock84/headcount · 80 tokens

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens

seo-strategy

Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…

cbrock84/headcount · 74 tokens

financial-statement-analysis

Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…

cbrock84/headcount · 93 tokens

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens

estimating-and-contingency

Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…

cbrock84/headcount · 87 tokens