KitchenMCP: Instructions file for Claude Code

CLAUDE.md

KitchenMCP CLAUDE.md is an instructions file for Claude Code from horatio8/KitchenMCP. It costs 843 tokens per session, scanned A, original, MIT.

A set of project instructions for a hosted Kitchen.co client portal used by Teller Consulting. It defines working agreements and a process for sending finished documents to clients for approval.

In plain words
What is it for?
Use it when preparing client documents, embedding Google documents, granting client access, and following the repository's development rules.
Why use it?
It keeps client deliverables in the required shared folders and uses the portal's approval and sharing rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is horatio8/KitchenMCP's own configuration. It tells Claude Code how to work on KitchenMCP 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 KitchenMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to horatio8/KitchenMCP. 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/horatio8/KitchenMCP/claude/kitchen-mcp-server-yaxsga/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/horatio8/KitchenMCP

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 KitchenMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/horatio8/kitchenmcp/claude-md/github.svg)](https://agentmods.dev/instructions/horatio8/kitchenmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/horatio8/kitchenmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/horatio8/kitchenmcp/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.

agentmods 80×15 button for KitchenMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/horatio8/kitchenmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/horatio8/kitchenmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 843 This file is loaded in full into every session.
When invoked 843 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00843 $0.00843
Opus 5.5 $0.00337 $0.00337
Sonnet 5.5 $0.00169 $0.00169
Haiku 4.5 $0.00084 $0.00084

Measured 10d ago against content hash 183af98740a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

KitchenMCP 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 10d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KitchenMCP

A hosted MCP server for the Kitchen.co client portal, used by Teller Consulting (workspace teller.kitchen.co).

Working agreements

  • Answer in dot points. Standing instruction.
  • Out of scope unless asked for directly: electoral-law or authorisation compliance, and the workflow-automation layer (src/workflow/, WORKFLOW_TOOLS_ENABLED, off by default — do not volunteer it).
  • Do not open a pull request unless explicitly asked.
  • Develop and push on claude/kitchen-mcp-server-yaxsga.

Sending a finished artefact for approval

Follow docs/APPROVAL-PATTERN.md whenever a deliverable goes to a client for approval. In short: verbatim copy into a Google Doc, client gets edit access, file it under Teller > Clients > <Client> in Drive as the archive, then embed that doc in the client's shared Kitchen folder and grant the client membership.

Use an embed (pe_…) for this, never a doc (doc_…). A Kitchen doc has no writable body, so a doc can be created and never filled.

Embedded Google documents must open without a login

Every Google document embedded in Kitchen is shared with anyone with the link, role writer:

share_file  fileId: <id>  permissionId: "anyoneWithLink"  role: "writer"

The client is not in the Teller Google Workspace. Share it with named accounts only and the embed shows them a Google sign-in wall inside the portal. Set this before embedding, confirm it with get_file_permissions, then pass link_sharing_confirmed: true to kitchen_create_embed.

This does mean anyone holding the URL can edit. That is a deliberate trade for login-free editing; see the tradeoff note in docs/APPROVAL-PATTERN.md and do not use it for contents that would matter in a stranger's hands.

Client work must live in a shared folder

Any tool that exposes a doc or embed to a client checks first that a shared client folder exists, and stops to ask if one does not. Do not weaken that guard to get a call through; if the precondition fails, surface the question to the person making the request.

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 843 tokens per session scan A 183af98740a9

Subscribe to this mod's changes

KitchenMCP CLAUDE.md is an instructions file published in the GitHub repository horatio8/KitchenMCP (0 stars, last pushed 11d ago), licensed MIT. It adds 843 tokens to every session, about $0.0034 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 2026-11-08.

Related

KitchenMCP CLAUDE.md compared with instructions from other repositories

KitchenMCP CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
KitchenMCP CLAUDE.mdhoratio8/KitchenMCPInstructions file011d agoMITA843Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot