What is workshop-harness CLAUDE.md?

Repository instructions for Workshop Harness, a toolkit for technical workshops with automation, document templates, and specialized coding-agent skills. They define how agents should work in the project, including required web checks for current workshop code.

They are for building workshops, hands-on labs, curriculum, notebooks, and automation with the Workshop Harness. They also guide the use of its command-line tool, skills, templates, and supported coding agents.

They give coding agents the project’s expected commands, structure, and safety rules before they generate workshop materials or modify files. This helps avoid outdated SDK examples and inconsistent project workflows.

How JAICHANGPARK/workshop-harness configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to JAICHANGPARK/workshop-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/JAICHANGPARK/workshop-harness/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/JAICHANGPARK/workshop-harness

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jaichangpark/workshop-harness/claude-md/github.svg)](https://agentmods.dev/instructions/jaichangpark/workshop-harness/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jaichangpark/workshop-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/jaichangpark/workshop-harness/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jaichangpark/workshop-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/jaichangpark/workshop-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,536 This file is loaded in full into every session.

When invoked 2,536 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02536	$0.02536
Opus 5.5	$0.01014	$0.01014
Sonnet 5.5	$0.00507	$0.00507
Haiku 4.5	$0.00254	$0.00254

Measured 6d ago against content hash 228c09ea907e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workshop-harness CLAUDE.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 6d 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.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Claude Code Agent Instructions for Workshop Harness

Standard Claude Code Context & Instructions for Workshop Harness (21 Agent Skills)

This repository provides native compatibility with Anthropic Claude Code CLI, Claude Sonnet 5.5 / Claude Opus 5.5 / Claude Fable 5.1, and Claude Desktop.

🎯 Repository Overview & Claude Code Role

workshop-harness is an AI Agent Harness, Skill Suite, and CLI Automation Toolkit for technical workshops (Build with AI, DevFest, Hands-on Labs).

🤖 CRITICAL RULES FOR CLAUDE CODE:

🌐 Mandatory Autonomous Pre-Flight Web Search (workshop-web-researcher):
- Never rely on static model training data. AI training weights contain obsolete/deprecated APIs and retired model tags.
- Claude Code MUST AUTONOMOUSLY execute live web searches (search_web / web search) before generating any workshop code, Colab notebooks, or curriculum to verify current SDK methods, modern imports, and active model tags (e.g. gemini-4-argon, gemini-3.8-flash, gemini-3.8-live, claude-sonnet-5.5, claude-opus-5.5, gpt-6-astra, gpt-6.1-sol, gemma4, google-genai, google-adk, google-agents-cli, com.google.genai, genui).
🌍 Developer-Friendly Terminology & Bilingual Technical Term Notation (영어 원문 병기 & 직역 금지):
- When generating or localizing documentation, .md files, presentation slides, runbooks, setup guides, or code comments in Korean, Japanese, or Chinese, do NOT use awkward literal machine translations.
- Always use real-world developer terminology AND include the original English technical term alongside it (개발자 친화적 용어 (English Original)):
  - Korean (KO) + English Original: "핸즈온 랩 (Hands-on Lab)", "스캐폴딩 (Scaffolding)", "런북 (Runbook)", "프롬프트 엔지니어링 (Prompt Engineering)", "구조화 출력 (Structured Outputs)", "툴 콜링 (Tool Calling)", "검색 증강 생성 (RAG, Retrieval-Augmented Generation)", "임베딩 (Embedding)", "양자화 (Quantization)", "추론 예산 (Thinking Budget)", "멀티 에이전트 오케스트레이션 (Multi-Agent Orchestration)", "의존성 주입 (Dependency Injection)", "폴백 (Fallback)" (Never ❌ "손으로 하는 실험실", ❌ "달리는 책", ❌ "발판 설치", ❌ "생각 예산").
  - Japanese (JA) + English Original: 「ハンズオンラボ (Hands-on Lab)」, 「デプロイ (Deploy)」, 「スキャフォールディング (Scaffolding)」, 「構造化出力 (Structured Outputs)」, 「量子化 (Quantization)」, 「ランブック (Runbook)」.
  - Chinese (ZH) + English Original: 「实战工作坊 (Hands-on Lab)」, 「脚手架 (Scaffolding)」, 「结构化输出 (Structured Outputs)」, 「量化 (Quantization)」, 「演练手册 (Runbook)」.
  - Code Comments: Preserve exact English identifiers (root_agent, FunctionTool, thinking_budget, response_schema) and pair localized comments with English technical terms in parentheses. See docs/agents-spec/terminology-and-style-guide.md.
🚫 Typography Rule (No Em Dash in Markdown & Documentation):
- NEVER generate em dash characters (\u2014) anywhere in generated .md files, documentation, slides, code comments, or runbooks. Always use standard hyphens (-), colons (:), or parentheses ().
- Run python3 harness_cli.py audit-typography --target <dir> --fix to audit and sanitize markdown typography automatically.
🚫 No Emojis in Documentation (Default: Clean Professional Text):
- Do NOT use emojis in generated documentation, slide decks, setup guides, code comments, or runbooks by default.
- Emojis may only be used if the user explicitly requests them in their prompt.
Natural Language Autonomy:
- Users communicate using natural language prompts. Do NOT ask users to execute Python CLI commands directly.
- When a user asks a question or makes a request, Claude Code must autonomously read the corresponding skill file (skills/*/SKILL.md) and execute the required Python tool or generate the artifacts on behalf of the user.

Read the full file on GitHub · 98 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.

6d ago Changed · +3 lines · +366 tokens per session 228c09ea907e
18d ago Changed · +5 lines · +277 tokens per session 1bc1a36e8f5e
2mo ago First seen · 90 lines · 1,893 tokens per session scan A 869d8aa4d481

Subscribe to this mod's changes

workshop-harness CLAUDE.md is an instructions file published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed 3d ago), licensed MIT. It adds 2,536 tokens to every session, about $0.0101 per session on Opus 5.5. 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.

workshop-harness CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
workshop-harness CLAUDE.mdJAICHANGPARK/workshop-harness	Instructions file	5	3d ago	MIT	A	2,536	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

workshop-harness: Instructions file for Claude Code