demo-mcp: Instructions file for Claude Code

CLAUDE.md

demo-mcp CLAUDE.md is an instructions file for Claude Code from MickaelV0/demo-mcp. It costs 1,145 tokens per session, scanned A, original, MIT.

Project instructions for demo-mcp, a private shared-memory proof of concept using OKF Markdown notes and links. They describe the Cloudflare Worker API, web app, shared schemas, plugin, and local development setup.

In plain words
What is it for?
Use them when changing, running, or debugging the demo-mcp codebase and its local services.
Why use it?
They give Claude Code the project layout, required authentication, development commands, and repository-specific cautions.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is MickaelV0/demo-mcp's own configuration. It tells Claude Code how to work on demo-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 demo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MickaelV0/demo-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/MickaelV0/demo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MickaelV0/demo-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 demo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mickaelv0/demo-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mickaelv0/demo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mickaelv0/demo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mickaelv0/demo-mcp/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 demo-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mickaelv0/demo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mickaelv0/demo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,145 This file is loaded in full into every session.
When invoked 1,145 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 $0.01145 $0.01145
Opus 5 $0.00573 $0.00573
Sonnet 5 $0.00229 $0.00229
Haiku 4.5 $0.00114 $0.00114

Measured 8d ago against content hash db5f2619e9f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

demo-mcp 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 8d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@.claude/stack.yml

demo-mcp

Private shared memory POC (Silex talk MCP + second cerveau): OKF markdown notes + links, same brain via web UI and MCP. Cloudflare Worker (Hono) + D1, single origin demo-mcp.roxabi.dev.

Layout

Path Role
apps/api Hono Worker — REST + MCP (POST /mcp) + D1 + optional Vectorize/AI
apps/web Vite SPA — TanStack Router + React Query, served as Worker assets
packages/shared OKF parser/validator + Zod schemas (the only place schemas live)
plugins/demo-mcp Claude Code plugin — MCP + skills
.claude-plugin/ Marketplace manifest (repo root = marketplace)

Local dev

cp apps/api/.dev.vars.example apps/api/.dev.vars   # else every /api/* and /mcp → 503
bun run db:migrate:local
bun run dev:api                                     # :8787 (auto-shifts if taken — check the wrangler line)

All /api/* and /mcp require the key (Authorization: Bearer … or X-API-Key); GET /health is the only public route.

Deviations from the fleet norm

Only what this repo does differently — everything else is inherited from ~/projects/CLAUDE.md and its ssot/*.ssot.md shards.

  • Branch from main. This repo has no staging branch; conventions.ssot.md scopes the staging default to roxabi-factory / roxabi-plugins / roxabi-live / roxabi-boilerplate, which does not include demo-mcp.
  • No docs/standards/ tree. There is no standards doc to read before coding, and .claude/stack.yml omits the standards: block rather than point at files that do not exist. Follow the surrounding code and the Gotchas below.
  • No .env, by design — the Worker reads apps/api/.dev.vars; public config lives in wrangler.toml [vars], secrets via wrangler secret put.
  • apps/api has no tests. Its test script carries --pass-with-no-tests, so a green CI proves nothing about the Worker.

Why no Critical Rules block here: /env-setup scaffolds one (dev process, tiers, git prohibitions, worktree, delegation, artifacts). It was removed on purpose — ssot/operator.ssot.md already states /dev #N as the single entry with the S/F-lite/F-full tiers, the ¬--force ¬--hard ¬--amend rule and "∃ matching skill → use it", and the rest is generic dev-core convention the skills carry themselves. A second copy here is not just noise: it silently contradicts the SSoT the day a shard changes. Do not let a re-run re-add it.

Read the full file on GitHub · 64 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. 8d ago First seen · 64 lines · 1,145 tokens per session scan A db5f2619e9f6

Subscribe to this mod's changes

demo-mcp CLAUDE.md is an instructions file published in the GitHub repository MickaelV0/demo-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,145 tokens to every session, about $0.0057 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 2026-09-01.

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 · 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 · 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 · 6,785 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 · 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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens