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 instructions/jackyyang258/agent-teacher/agents-mdgit clone --depth 1 https://github.com/JackyYang258/agent-teacherWrote 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/instructions/jackyyang258/agent-teacher/agents-md)<a href="https://agentmods.dev/instructions/jackyyang258/agent-teacher/agents-md"><img src="https://agentmods.dev/badge/instructions/jackyyang258/agent-teacher/agents-md.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 | $0.02297 | $0.02297 |
| Opus 5 | $0.01149 | $0.01149 |
| Sonnet 5 | $0.00459 | $0.00459 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
agent-teacher AGENTS.md 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentTeacher Agent Guide
Personal/global agent rules may live outside this repository. This file records AgentTeacher-specific repository maps, Working Rules, Current Risk Areas, Verification, and Release Flow.
Project
AgentTeacher is a Claude Code skill that teaches concepts through a fixed six-part spine: intuition → example (runnable or pseudocode) → code walkthrough → trap → pointers → test questions. It is deliberately small — one SKILL.md, a handful of references, a handful of evals and worked examples, one packaging script. The whole project should fit in a few hundred lines of markdown plus shell.
The skill output is delivered in conversation, not as files. The only artifacts written to disk are (a) the Mode B pseudocode sidecar for editor viewing, and (b) the full-lesson file when the user explicitly asks to save.
Repository Map
SKILL.md— skill entrypoint: triggering, language choice, the six-layer spine, output rules, anti-patterns.README.md/README.zh-CN.md— user-facing project intro and install instructions (bilingual, full parity).CONTRIBUTING.md/CONTRIBUTING.zh-CN.md— contribution flow and bilingual policy (bilingual, full parity).CLAUDE.md— Claude-specific entry pointing here, with the project-specific hard rules.LICENSE— MIT.references/teaching-method.md— per-layer playbook with good/bad examples. The craft of each layer lives here.references/code-style-for-teaching.md— rules for teaching code: Mode A (runnable + trace blocks for algorithms), Mode B (the three pseudocode flavors).references/concept-to-language.md— concept area → recommended code language and Mode A/B form.references/enrichments.md— the eight optional enrichments (math tier, state tracking, design rationale, cousin matrix, prerequisites + variants, misconception list, visualization, invariants) and the decision checklist for when each fires.evals/evals.json— test prompts with expected-output descriptions (closure, CAP, GIL, monad, GRPO, MoE).assets/examples/— worked example outputs frozen from running the skill. Examples are bilingual: each concept has<name>-en.mdand<name>-zh.mdplus a shared language-agnostic<name>-pseudocode.pysidecar. New examples should ship in both languages; one-language contributions are accepted and a maintainer translates the other side.scripts/package-skill.sh— builds the release archive..claude-plugin/marketplace.json— Claude Code plugin marketplace metadata.dist/agent-teacher.zip— tracked release archive.
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 · 83 lines · 2,297 tokens per session scan A 3580393cfd94
agent-teacher AGENTS.md is an instructions file published in the GitHub repository JackyYang258/agent-teacher (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,297 tokens to every session, about $0.0115 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.
Other instructions, from other repositories
promptasy CLAUDE.md
Claude Code instructions for romanticamaj/promptasy, covering promptasy, 這份文件是什麼, /goal — 長期、開放、不設限方向的目標, 遊戲願景與核心體驗 and 設計支柱（design pillars）.
promptasy AGENTS.md
AGENTS.md instructions for romanticamaj/promptasy, covering agents.md — promptasy 工程 harness, 專案一句話, 每個 phase 的節奏, 測試金字塔（由快到慢） and 測試策略（成本控制的核心）.
avoid-ai-writing CLAUDE.md
Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
harness-anchor CLAUDE.md
Instructions for Redtropig/harness-anchor, covering harness-anchor — contributor & ai collaborator guidelines, if you are an ai agent editing this plugin, design invariants (do not break), shell hazards no tool in this repo catches and authoring a new skill (when explicitly asked).