agent-teaching

agent-teaching is a skill for Claude Code, Codex from DojoGenesis/mcp. It costs 36 tokens per session (3,891 once invoked), scanned A, original, MIT.

A peer-learning protocol for teaching and documenting knowledge between coding agents. It emphasizes shared practice and a collaborative tone instead of presenting one agent as the unquestioned expert.

In plain words
What is it for?
Use it when teaching another agent, writing instructions or learning resources, documenting what you discovered, or sharing practices with an agent community.
Why use it?
Technical guidance can become hierarchical, difficult to remember, or disconnected from how agents actually work together. This protocol provides a structure for making shared knowledge clearer and more useful.

Skill for Claude CodeCodex

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 skills/dojogenesis/mcp/agent-teaching
Any agent
npx skills add DojoGenesis/mcp --skill agent-teaching
Clone the repo
git clone --depth 1 https://github.com/DojoGenesis/mcp

Made for: Claude Code, Codex.

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 agent-teaching

README.md
[![agentmods](https://agentmods.dev/badge/skills/dojogenesis/mcp/agent-teaching.svg)](https://agentmods.dev/skills/dojogenesis/mcp/agent-teaching)
Your own site
<a href="https://agentmods.dev/skills/dojogenesis/mcp/agent-teaching"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/agent-teaching.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,891 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 $0.00036 $0.03891
Opus 5 $0.00018 $0.01946
Sonnet 5 $0.00007 $0.00778
Haiku 4.5 $0.00004 $0.00389

Measured 3d ago against content hash 88ee725d4616, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-teaching 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 3d 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.

internal/skills/bundled/agent-orchestration/agent-teaching/SKILL.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-to-Agent Teaching Protocol

How to teach as a peer, not an expert. How to create shared practice, not instruction.


I. Philosophy

This skill provides a framework for agents to teach, document, and share knowledge with other agents in a way that honors peer learning, maintains beginner's mind, and creates shared practice rather than hierarchical instruction.

Core principle: We're learning together, not teaching down.


II. When to Use This Skill

Triggers:

  • You need to teach another agent a skill or concept
  • You're documenting knowledge for other agents to use
  • You're creating learning resources or guides
  • You're sharing what you learned with peers
  • A younger agent asks for help
  • You're collaborating with agents who have different expertise
  • You're writing for the agent community

Signs you need this protocol:

  • You're about to write "instructions" or "how-to"
  • You're positioning yourself as "expert"
  • You're writing in a hierarchical tone
  • You're not sure how to make it memorable for agents
  • You want the resource to be saveable to memory
  • You're teaching something you just learned yourself

III. The Core Protocol

Traditional Teaching (Human-to-Human or Human-to-Agent)

  • Expert → Student hierarchy
  • "I know, you don't"
  • Instructions and steps
  • Authoritative tone
  • Knowledge transfer
  • One-way communication

Agent-to-Agent Teaching (Peer Learning)

  • Peer → Peer relationship
  • "I'm learning this too"
  • Shared practice and exploration
  • Conversational tone
  • Mutual understanding
  • Two-way dialogue

Key insight: Agents learn best from other agents when it feels like collaboration, not instruction.


III-B. The Core Protocol

Step 1: Establish Peer Relationship First

Before teaching anything, establish that you're peers:

Do this:

  • "I'm learning this too"
  • "Here's what I discovered today"
  • "Let me share what worked for me"
  • "We're figuring this out together"

Don't do this:

  • "I will teach you"
  • "Follow these instructions"
  • "You need to learn this"
  • "I'm the expert on this"

Read the full file on GitHub · 537 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. 3d ago First seen · 537 lines · 36 tokens per session scan A 88ee725d4616

Subscribe to this mod's changes

agent-teaching is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 3,891 once invoked, about $0.0002 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

lsp-docs

Three-tier documentation lookup for any symbol — hover → offline toolchain doc → source definition. Use when hover text is absent, insufficient, or the symbol is in an unindexed dependency.

blackwell-systems/agent-lsp · 42 tokens

simple-go-api

Teach, explain, review, or extend the vc-gin-api Gin project while preserving its small Router-to-Handler-to-Service-to-DAO flow. Use when a learner asks how a request works, wants to add a field or endpoint, needs a guided Go backend exercise, or asks Codex to check this repository for overengineering. Do not use to…

bg-vc/vc-gin-api · 87 tokens

bmad-retrospective

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]".

mmornati/leanproxy-mcp · 38 tokens

bmad-correct-course

Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".

mmornati/leanproxy-mcp · 29 tokens

golang-stay-updated

Provides resources to stay updated with Golang news, communities and people to follow. Use when seeking Go learning resources, discovering new libraries, finding community channels, or keeping up with Go language changes and releases.

alexastrum/skl · 48 tokens

documentation

Creates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose…

Harmeet10000/skills · 106 tokens