What is registrum-mcp CLAUDE.md?

A set of project instructions for maintaining and publishing the Registrum MCP server, a TypeScript service that exposes an API to AI clients. It also documents checks for endpoint, parameter, and description coverage.

Use it when building, testing, publishing, and checking the npm package @registrum/mcp and its API-to-tool coverage.

It makes clear that pushing code is not enough: the package must be published and verified before users receive the changes.

How vdmeu/registrum-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vdmeu/registrum-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/vdmeu/registrum-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vdmeu/registrum-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vdmeu/registrum-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vdmeu/registrum-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vdmeu/registrum-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vdmeu/registrum-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.

Your own site · 80×15

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

Per session 766 This file is loaded in full into every session.

When invoked 766 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	$0.00766	$0.00766
Opus 5	$0.00383	$0.00383
Sonnet 5	$0.00153	$0.00153
Haiku 4.5	$0.00077	$0.00077

Measured 9d ago against content hash e327fdd20f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

registrum-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 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@registrum/mcp - Claude Code Instructions

MCP server exposing the Registrum API to LLM clients. TypeScript, published to npm as @registrum/mcp. Root: /c/users/eugen/claude-ch-proj/mcp. Repo: vdmeu/registrum-mcp.

npm run build        # tsc
npm test             # vitest
node scripts/check-endpoint-coverage.mjs     # every API endpoint has a tool
node scripts/check-param-drift.mjs           # every param a tool sends is declared
node scripts/check-description-drift.mjs     # descriptions still describe what the API returns

DONE = PUBLISHED AND CONSUMED. A push here ships nothing.

This repo has the longest gap between "pushed" and "a user is served it", and it is the one place where a green test suite is most misleading. Two hops, both required:

Publish. npm version patch (its version script syncs server.json) then git push --follow-tags. The tag fires publish.yml, which publishes via OIDC trusted publishing - no token, nothing to expire. Verify with npm view @registrum/mcp version, and for anything textual grep the packed tarball (npm pack @registrum/mcp@<v>), because the version number only proves a release happened, not that it carries your change.
Bump the consumer. The hosted endpoint at registrum.co.uk/api/mcp imports registerTools from this package rather than redefining the tools, so it serves whatever the website lockfile pins. npm install @registrum/mcp@<version> in website/, commit, push. A ^range in package.json does not move a pinned package-lock.json.

Skipping step 1 leaves everyone on the old version; skipping step 2 leaves every hosted user on it. Both happened on 2026-08-30 with the ECCTA description fix (#20).

Ship bugfixes without asking - a patch release is a normal release, not an irreversible action needing sign-off.

The tool description IS the interface

A field the description never names is a field the model never asks about, so this package can be correct, shipped, and useless at once. get_psc_chain returned ECCTA verification for months without saying so (#20).

Read the full file on GitHub · 57 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.

9d ago First seen · 57 lines · 766 tokens per session scan A e327fdd20f72

Subscribe to this mod's changes

registrum-mcp CLAUDE.md is an instructions file published in the GitHub repository vdmeu/registrum-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 766 tokens to every session, about $0.0038 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.

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

registrum-mcp: Instructions file for Claude Code