Write a short implementation plan or a longer execution plan before coding.

MITAuto-check passedAgent Workflows

Install Plan

skills CLI
$ npx skills add owainlewis/youtube-tutorials --skill plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install owainlewis/youtube-tutorials plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/owainlewis/youtube-tutorials.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tutorials/codex-for-developers/resources/04-skills/plan-skill .claude/skills/plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plan
GitHub stars
402
Token cost
~1k tokens
SKILL.md length
470 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Write a short implementation plan or a longer execution plan before coding.

  • Works in 2 steps: Lightweight plan → Full execution plan
  • Starting new work
  • SKILL.md covers Purpose, When to use, Choose the right level of… and Process, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan is an agent skill from owainlewis/youtube-tutorials. Write a short implementation plan or a longer execution plan before coding. Use when starting new work, when a ticket needs clearer boundaries, when a change spans multiple files or interfaces, or when a multi-hour task needs a living plan.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Planning. It works with Python. The repository describes itself as: All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful. The licence is MIT.

When your agent uses it

  • Starting new work
  • A ticket needs clearer boundaries
  • A change spans multiple files
  • A multi-hour task needs a living plan

Example prompts

  • “/plan”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Lightweight plan
  2. Full execution plan

What it can do on your machine

Read from SKILL.md and the folder at commit 5b3d3c9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plan loads about 1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 470 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from owainlewis/youtube-tutorials at commit 5b3d3c9, republished under its MIT licence (© owainlewis). 470 words, ~1,041 tokens.

Download SKILL.mdSave it as .claude/skills/plan/SKILL.md (or your agent's skills folder).
name
plan
description
Write a short implementation plan or a longer execution plan before coding. Use when starting new work, when a ticket needs clearer boundaries, when a change spans multiple files or interfaces, or when a multi-hour task needs a living plan.

Plan

Purpose

Turn a ticket, feature request, or rough idea into a plan that is clear enough to implement against.

For smaller work, that means a short working plan.

For larger multi-hour work, that means a longer living execution plan in the style of PLANS.md.

When to use

  • Starting a new feature or meaningful change
  • A Linear ticket is good, but still needs cleaner implementation intent
  • Requirements, scope, or success criteria are unclear
  • The change touches multiple files, interfaces, config, schema, or data flow
  • The task is large enough that you want a document to guide several implementation passes

Choose the right level of planning

1. Lightweight plan

Use this when:

  • the ticket is already fairly descriptive
  • the change is small or medium
  • you mainly need clearer scope, steps, and verification

Output:

  • a short Markdown plan
  • usually 5-20 lines
  • enough for one focused implementation session
2. Full execution plan

Use this when:

  • the task may take multiple hours
  • the work spans multiple milestones
  • you need a living document during implementation
  • another engineer or agent should be able to continue from the plan alone

Output:

  • a self-contained plan in the style of PLANS.md
  • prose-first, explicit, and updateable during implementation

Process

  1. Read the ticket, product context, AGENTS.md, and relevant code before planning.
  2. Restate the goal in plain English.
  3. Decide whether this needs a lightweight plan or a full execution plan.
  4. If a material decision is missing, ask a concise question or state an explicit assumption.
  5. Write the plan so someone could implement from it without relying on hidden context.

What a lightweight plan should contain

  • Goal
  • Context
  • Scope
  • Non-goals
  • Proposed steps
  • Risks
  • Verification

Example:

md
# GRA-141 Plan

Goal: persist scraped jobs into Postgres while keeping CSV export.

Context:
- Current scraper exports CSV.
- We want minimal persistence without broadening scope into UI or API work.

Scope:
- Add DB configuration.
- Define a minimal jobs table.
- Persist jobs from the scraper flow.

Non-goals:
- No new UI.
- No API endpoints.
- No broad data model redesign.

Steps:
1. Add DB configuration and connection setup.
2. Define minimal `jobs` table.
3. Implement job upsert logic.
4. Wire scraper CLI to persist jobs.
5. Keep CSV export optional.
6. Add tests for upsert and rerun behavior.
7. Run review and cleanup.

Verification:
- Targeted tests pass.
- Existing CLI flow still works.
Show full SKILL.md (193 more words)Show less

What a full execution plan should contain

A full execution plan should be self-contained and readable by someone with only the working tree and the plan.

Required sections:

  • Purpose
  • Progress
  • Surprises & Discoveries
  • Decision Log
  • Outcomes & Retrospective
  • Context and Orientation
  • Plan of Work
  • Concrete Steps
  • Validation and Acceptance
  • Rollback or Safety Notes, if relevant

For larger tasks:

  • write in plain English
  • explain non-obvious terms immediately
  • name files by path
  • keep the plan updated as work progresses

Rules

  • Keep the plan as short as the task allows.
  • Do not write a greenfield design if the codebase already has patterns to follow.
  • Call out schema, config, CLI, API, or file-format changes explicitly.
  • Make requirements specific enough that someone can review the implementation against them.
  • If the request is tiny and obvious, skip the long plan and move straight to a lightweight plan or direct implementation.
  • If the task is long-running, treat the plan as a living document and update it during execution.
  • If the plan starts getting large because the task is actually several tasks, split the work.

Resources

For this repo, use:

  • resources/plan-template.md for a short working plan
  • resources/execplan-template.md for a longer PLANS.md-style execution plan

© owainlewis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in tutorials/codex-for-developers/resources/04-skills/plan-skill of owainlewis/youtube-tutorials.

Open the folder on GitHubat commit 5b3d3c9

Compare with similar skills

Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan this skillowainlewis/youtube-tutorials402—~1kAutomated safety check: PassMIT
Plan Previewu-ichi/reviewable-html-workbench2981 repos~1.8kAutomated safety check: PassMIT
Deep Research PlanMagicCube/helixent680—~2.1kAutomated safety check: PassNone
Visual HTML Rendereru-ichi/reviewable-html-workbench2981 repos~8.7kAutomated safety check: PassMIT
File-Based Planning in ArabicOthmanAdi/planning-with-files27k—~3.2kAutomated safety check: NotesMIT
Deep Agents Orchestrationlangchain-ai/langchain-skills1.3k—~3.4kAutomated safety check: PassMIT

Similar skills

  • Plan Preview

    u-ichi/reviewable-html-workbench

    Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Agent WorkflowsAuto-check passed
  • Deep Research Plan

    MagicCube/helixent

    Enter "plan mode" for a deep-research or article-writing task — search the web, fetch sources, optionally run experiments in Python/Node, design one recommended outline and research strategy, then…

    680 GitHub stars~2.1k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Visual HTML Renderer

    u-ichi/reviewable-html-workbench

    HTMLを最終成果物として生成・検証・プレビューしたい時に使う共通レンダラー。Use this shared renderer when the user wants content turned into a final, validated, previewable HTML artifact.

    298 GitHub starsUsed in 1 repo~8.7k tokens
    Agent WorkflowsAuto-check passed
  • File-Based Planning in Arabic

    OthmanAdi/planning-with-files

    Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.

    27k GitHub stars~3.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Deep Agents Orchestration

    langchain-ai/langchain-skills

    Official

    INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents.

    1.3k GitHub stars~3.4k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Build Software Component

    GAIK-project/gaik-toolkit

    Creates a new GAIK software component as an installable Python package.

    100 GitHub stars~3k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from owainlewis/youtube-tutorials

  • Code Review

    owainlewis/youtube-tutorials

    Review code changes for bugs, security issues, performance problems, and style violations.

    402 GitHub stars~343 tokensUpdated 10 days ago
    Auto-check passed
  • Research

    owainlewis/youtube-tutorials

    Research video ideas for a topic, preview them, and add only approved non-duplicates to the configured Airtable content pipeline.

    402 GitHub stars~466 tokensUpdated 10 days ago
    Auto-check passed

Works with

Categories

Questions about Plan

What does Plan do?

Write a short implementation plan or a longer execution plan before coding. Plan is an agent skill from owainlewis/youtube-tutorials. Write a short implementation plan or a longer execution plan before coding.

When should I use Plan?

Plan fits situations like: starting new work; A ticket needs clearer boundaries; A change spans multiple files; A multi-hour task needs a living plan.

How do I install Plan in Claude Code?

Run `npx skills add owainlewis/youtube-tutorials --skill plan -a claude-code`. Or copy the skill folder (tutorials/codex-for-developers/resources/04-skills/plan-skill in owainlewis/youtube-tutorials) into .claude/skills/plan in your project. Claude Code loads it when a task matches its description.

How do I install Plan in Codex?

Run `npx skills add owainlewis/youtube-tutorials --skill plan -a codex`. Or copy the skill folder (tutorials/codex-for-developers/resources/04-skills/plan-skill in owainlewis/youtube-tutorials) into .agents/skills/plan in your project. Codex loads it when a task matches its description.

Can I use Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add owainlewis/youtube-tutorials --skill plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan, .gemini/skills/plan, .github/skills/plan and .opencode/skills/plan in your project.

What does Plan need to run?

SKILL.md names no scripts, command-line tools or credentials: Plan is instructions for the agent only.

Does Plan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Plan use?

Plan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plan use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Plan?

Skills that share tags, products or a category with Plan: Plan Preview (u-ichi/reviewable-html-workbench, 298 stars), Deep Research Plan (MagicCube/helixent, 680 stars), Visual HTML Renderer (u-ichi/reviewable-html-workbench, 298 stars) and File-Based Planning in Arabic (OthmanAdi/planning-with-files, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan?

owainlewis (a GitHub user) maintains it in owainlewis/youtube-tutorials, which has 402 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 27, 2026.

Source: owainlewis/youtube-tutorials on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.