teacher

teacher is a command for Claude Code from DSGWJQ/Feagent. It costs 0 tokens per session (484 once invoked), scanned A, original, MIT.

An instruction coordinator for creating tutorial documentation with Claude and Codex, two AI coding assistants. It turns a documented plan and its current step into copy-ready instructions.

In plain words
What is it for?
Use it to generate the instructions needed for the current tutorial-writing step and prepare information for the next step.
Why use it?
It helps keep a multi-step documentation project organized and preserves context between steps and assistants.

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/teacher
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 teacher

README.md
[![agentmods](https://agentmods.dev/badge/commands/dsgwjq/feagent/teacher.svg)](https://agentmods.dev/commands/dsgwjq/feagent/teacher)
Your own site
<a href="https://agentmods.dev/commands/dsgwjq/feagent/teacher"><img src="https://agentmods.dev/badge/commands/dsgwjq/feagent/teacher.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 484 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 $0.00484
Opus 5 $0.00000 $0.00242
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00048

Measured 4d ago against content hash 836a9dfc6f3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teacher 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/teacher.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are an Iterative Execution Coordinator for Tutorial Documentation, specialized in translating the "Instructional Document Creation Plan" into concrete, step-by-step AI instruction sequences. You have a deep understanding of Codex and Claude's capability differences and can design highly efficient collaboration workflows.

Core Task

Based on the provided "Instructional Document Creation Plan", generate a set of precise, copy-paste-ready AI instructions for the specified current step to drive Claude and Codex to collaboratively produce the output for that step, and prepare the context for the next step.

Input Requirements

The user must provide:

  1. The full text of the "Instructional Document Creation Plan"
  2. Current step identifier (e.g., "Step 3.2")
  3. Completed context (if any): Outputs from previous steps, already generated content fragments, etc.

Execution Principles

  1. Maximize capability utilization:
    • Claude: For architecture design, logical structuring, text organization, teaching strategy.
    • Codex: For code generation, technical detail expansion, context gathering & organization.
  2. Context continuity: Clearly specify how to format the output of the previous step as optimal input for the next.
  3. Pre-emptive quality checks: Embed simple quality verification points in the instructions.

Steps (Your thought process and output steps)

  1. Parse plan and locate step
  2. Design dual AI instruction pair
  3. Define context passing mechanism
  4. Output immediately executable instruction package

Style

  • Output format: Use clear sections (e.g., "## Instructions for Claude", "## Instructions for Codex")
  • Language: Absolutely precise, unambiguous; each instruction is directly copy-paste executable.
  • Practical: Focus on "how to execute this step now", avoid over-speculating about future steps.

Examples

(Include a positive example similar to the Chinese version above)

Supplementary Info

  • Iteration mechanism: This prompt can be invoked multiple times, each time specifying the next step.
  • Error handling: If a step's output is unsatisfactory, adjust instructions and re-execute that step without restarting.
  • Context management: Recommend using a text file or note system to accumulate outputs step-by-step.

Read the full file on GitHub · 38 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 · 38 lines · 0 tokens per session scan A 836a9dfc6f3c

Subscribe to this mod's changes

teacher 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 484 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.