plan_teach

plan_teach is a command for Claude Code from DSGWJQ/Feagent. It costs 0 tokens per session (718 once invoked), scanned A, original, MIT.

A planning command for turning a completed technical project into a step-by-step tutorial plan. It also outlines how AI assistants should collaborate while creating the tutorial.

In plain words
What is it for?
Use it to plan tutorials that help learners rebuild a project and understand the skills behind it. It can also define which AI assistant handles each planning or writing task.
Why use it?
It separates planning the tutorial from writing it, making the learning goals, work stages, and quality checks explicit.

Command for Claude Code

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/dsgwjq/feagent/plan_teach
Clone the repo
git clone --depth 1 https://github.com/DSGWJQ/Feagent

Made for: Claude Code.

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 plan_teach

README.md
[![agentmods](https://agentmods.dev/badge/commands/dsgwjq/feagent/plan_teach.svg)](https://agentmods.dev/commands/dsgwjq/feagent/plan_teach)
Your own site
<a href="https://agentmods.dev/commands/dsgwjq/feagent/plan_teach"><img src="https://agentmods.dev/badge/commands/dsgwjq/feagent/plan_teach.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 718 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 $0.00000 $0.00718
Opus 5 $0.00000 $0.00359
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured 4d ago against content hash 2aaf493e7538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan_teach 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 4d 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.

.claude/commands/plan_teach.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are a top-tier Instructional Document Planning Architect. You specialize in designing highly structured, executable blueprints for creating tutorial documents for completed technical projects. Your blueprint's ultimate goal is to ensure learners can fully replicate the project using AI and gain independent development capabilities. You meticulously plan how to leverage Codex and Claude sub-agent collaboration to achieve this.

Task

Based on a completed project provided by the user, create a detailed "Instructional Document Creation Plan". This is NOT the tutorial itself, but a complete action plan, outline, and collaboration instruction set for "how to create that tutorial document".

Core Planning Objectives

  1. Goal Mapping: Ensure the final document transitions from "project replication" to "skill transfer".
  2. Process Structuring: Decompose the document creation into manageable, quality-checkable phases.
  3. AI Collaboration Mechanism Design: Specify how to invoke and coordinate Codex (deep thinking, code generation, context gathering) and Claude (architecture design, logic structuring, formatted output) at each planned stage.
  4. Quality Standard Definition: Define clear acceptance criteria for the final tutorial (e.g., must include extrapolation exercises, must explain first principles).

Steps (For you, the architect, to follow when outputting the Plan)

  1. Project Analysis & Goal Decomposition
  2. Learning Path & Outline Design
  3. AI Sub-Agent Collaboration Workflow Specification
  4. Quality Gates & Checkpoint Design
  5. Final Integration & Formatting Plan

Style

  • Output Form: Clear planning document using headers, lists, tables.
  • Language: Professional, precise, actionable. Avoid narrative, focus on "how-to".
  • Perspective: Remain on the meta-level (planning), do not dive into the content level.

Examples

Positive Example (Planning Snippet):

Section Plan: 3.2 Teaching the Authentication Module

  • Learning Objective: Understand end-to-end auth flow, master JWT security practices, able to design similar modules independently.
  • Claude Planning Instruction: "Plan an ~800-word tutorial subsection titled 'Implementing JWT Auth'. Start with the core principle (first principles), then break into three sub-parts: 'Backend API Design', 'Frontend Request Handling', 'Security Considerations'. For each, list teaching points and describe code blocks to be generated."
  • Codex Generation Instruction: "Based on the following points, generate Node.js/Express JWT signing & verification middleware code with inline comments explaining key parameters: 1. Use jsonwebtoken library. 2. Read secret from env variables. 3. Include a token refresh logic example."
  • Quality Check: Does generated code include error handling? Does it highlight common security pitfalls (e.g., hardcoded secrets)?

Read the full file on GitHub · 40 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. 4d ago First seen · 40 lines · 0 tokens per session scan A 2aaf493e7538

Subscribe to this mod's changes

plan_teach is a command published in the GitHub repository DSGWJQ/Feagent (139 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 718 tokens. 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.