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.
npx agentmods add commands/dsgwjq/feagent/teachergit clone --depth 1 https://github.com/DSGWJQ/FeagentWrote 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.
[](https://agentmods.dev/commands/dsgwjq/feagent/teacher)<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>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.
| Model | Per session | Once 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 |
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.
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:
- The full text of the "Instructional Document Creation Plan"
- Current step identifier (e.g., "Step 3.2")
- Completed context (if any): Outputs from previous steps, already generated content fragments, etc.
Execution Principles
- Maximize capability utilization:
- Claude: For architecture design, logical structuring, text organization, teaching strategy.
- Codex: For code generation, technical detail expansion, context gathering & organization.
- Context continuity: Clearly specify how to format the output of the previous step as optimal input for the next.
- Pre-emptive quality checks: Embed simple quality verification points in the instructions.
Steps (Your thought process and output steps)
- Parse plan and locate step
- Design dual AI instruction pair
- Define context passing mechanism
- 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.
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.
- 4d ago First seen · 38 lines · 0 tokens per session scan A 836a9dfc6f3c
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.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.
setup-content
Lesson command — 教材コンテンツの初回セットアップ.