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.
curl -O https://raw.githubusercontent.com/MickaelV0/demo-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/MickaelV0/demo-mcpWrote 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/mickaelv0/demo-mcp/claude-md)<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.
<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>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 | $0.01145 | $0.01145 |
| Opus 5 | $0.00573 | $0.00573 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
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.
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 nostagingbranch;conventions.ssot.mdscopes 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.ymlomits thestandards:block rather than point at files that do not exist. Follow the surrounding code and the Gotchas below. - No
.env, by design — the Worker readsapps/api/.dev.vars; public config lives inwrangler.toml [vars], secrets viawrangler secret put. apps/apihas no tests. Itstestscript carries--pass-with-no-tests, so a green CI proves nothing about the Worker.
Why no Critical Rules block here:
/env-setupscaffolds one (dev process, tiers, git prohibitions, worktree, delegation, artifacts). It was removed on purpose —ssot/operator.ssot.mdalready states/dev #Nas the single entry with the S/F-lite/F-full tiers, the¬--force ¬--hard ¬--amendrule 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.
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.
- 8d ago First seen · 64 lines · 1,145 tokens per session scan A db5f2619e9f6
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.
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.
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.
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).
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).
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.
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.