workshop-a2a-mcp: Instructions file for Claude Code

CLAUDE.md

workshop-a2a-mcp CLAUDE.md is an instructions file for Claude Code from axel-sirota/workshop-a2a-mcp. It costs 1,623 tokens per session, scanned A, original, Apache-2.0.

Instructions for developing a Jupyter notebook one cell at a time, rather than replacing the whole notebook at once. They describe how to count cells and append each new cell in the correct position.

In plain words
What is it for?
Use them when building or modifying the specified workshop notebook with notebook-editing tools.
Why use it?
They reduce the risk of overwriting existing notebook work and make each development step explicit and recoverable.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; names the NotebookEdit tool.

This is axel-sirota/workshop-a2a-mcp's own configuration. It tells Claude Code how to work on workshop-a2a-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything workshop-a2a-mcp configures โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to axel-sirota/workshop-a2a-mcp. 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/axel-sirota/workshop-a2a-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/axel-sirota/workshop-a2a-mcp

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 workshop-a2a-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/axel-sirota/workshop-a2a-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/axel-sirota/workshop-a2a-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/axel-sirota/workshop-a2a-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/axel-sirota/workshop-a2a-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

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

agentmods 80ร—15 button for workshop-a2a-mcp CLAUDE.md

Your own site ยท 80ร—15
<a href="https://agentmods.dev/instructions/axel-sirota/workshop-a2a-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/axel-sirota/workshop-a2a-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,623 This file is loaded in full into every session.
When invoked 1,623 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01623 $0.01623
Opus 5 $0.00812 $0.00812
Sonnet 5 $0.00325 $0.00325
Haiku 4.5 $0.00162 $0.00162

Measured 9d ago against content hash dbad33b7c11c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

workshop-a2a-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 9d 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 ยท 204 lines

How it starts

The opening of the file, as written. The whole thing โ€” 204 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Strict Implementation Rules

๐Ÿšจ CRITICAL: How to Build This Notebook

Rule 1: NEVER Write Full Files

  • WRONG: Creating entire notebook at once
  • RIGHT: Build cell by cell, appending to notebook
  • Use iterative approach: Plan โ†’ Build Cell โ†’ Next Cell

Rule 2: Cell-by-Cell Development Process

Follow this EXACT pattern for EVERY cell:

# Step 1: Count current cells
python3 -c "import json; nb = json.load(open('workshop_notebook.ipynb')); print(f'Current cells: {len(nb[\"cells\"])}')"

# Step 2: Calculate cell_id for next cell
# If you have N cells, use cell_id="cell-(N-1)" to append at position N

# Step 3: Add the cell using NotebookEdit
NotebookEdit(
    notebook_path="/path/to/notebook.ipynb",
    edit_mode="insert",
    cell_id="cell-X",  # X = current_cells - 1
    cell_type="markdown" or "code",
    new_source="content"
)

IMPORTANT PATTERN TO REMEMBER:

  • First cell: Don't specify cell_id (notebook is empty)
  • Second cell: Use cell_id="cell-0" (append after first cell)
  • Third cell: Use cell_id="cell-1" (append after second cell)
  • Fourth cell: Use cell_id="cell-2" (append after third cell)
  • Pattern: For cell N, use cell_id="cell-(N-2)" to append at end

Rule 3: Narrative Structure

EVERY section must follow this narrative flow:

  1. Hook - Why this matters
  2. Explain - What we're building
  3. Show - Visual or diagram
  4. Build - Code implementation
  5. Test - Verify it works
  6. Reflect - Key takeaway

Rule 4: Progressive Complexity Mandate

Start ridiculously simple, add complexity gradually:

# Cell 1: Simplest possible
agent = ChatOpenAI()
response = agent.invoke("What is cardiac arrest?")

# Cell 5: Add a tool
agent_with_tool = create_agent(tools=[search_tool])

# Cell 10: Add MCP
agent_with_mcp = create_agent(tools=[mcp_tools])

# Cell 20: Multi-agent
system = create_multi_agent_system()

Rule 5: Documentation Requirements

ENFORCE 50/50 Rule:

  • Every code cell MUST have preceding markdown cell
  • Markdown must be โ‰ฅ 3 sentences
  • Include WHY not just WHAT

Read the full file on GitHub ยท 204 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. 9d ago First seen ยท 204 lines ยท 1,623 tokens per session scan A dbad33b7c11c

Subscribe to this mod's changes

workshop-a2a-mcp CLAUDE.md is an instructions file published in the GitHub repository axel-sirota/workshop-a2a-mcp (2 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 1,623 tokens to every session, about $0.0081 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js ยท 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex ยท 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode ยท 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart โ€” add a new integration in 5 steps, integration architecture and integrationmanifest โ€” file tracking.

github/spec-kit ยท 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode ยท 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain ยท 4,469 tokens