Borrowing it
Nothing to install: this file belongs to Honeyfield-Org/ris-mcp-ts. 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/Honeyfield-Org/ris-mcp-ts/main/CLAUDE.mdgit clone --depth 1 https://github.com/Honeyfield-Org/ris-mcp-tsWrote 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/honeyfield-org/ris-mcp-ts/claude-md)<a href="https://agentmods.dev/instructions/honeyfield-org/ris-mcp-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/honeyfield-org/ris-mcp-ts/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/honeyfield-org/ris-mcp-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/honeyfield-org/ris-mcp-ts/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 | $0.12231 | $0.12231 |
| Opus 5 | $0.06116 | $0.06116 |
| Sonnet 5 | $0.02446 | $0.02446 |
| Haiku 4.5 | $0.01223 | $0.01223 |
Grade A, and why
ris-mcp-ts 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 yesterday.
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 — 786 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MCP Server for the Austrian Legal Information System (RIS - Rechtsinformationssystem).
Quick Start
pnpm install
pnpm run build
Development Commands
pnpm run dev # Start with tsx (hot reload, stdio)
pnpm run dev:http # Start HTTP server with tsx (hot reload)
pnpm run build # Compile TypeScript (runs typecheck first)
pnpm run gen:ui # Build the widget bundles → src/generated/<widget>-html.ts
pnpm start # Run compiled version (stdio)
pnpm run start:http # Run HTTP server (Streamable HTTP transport)
pnpm run check # typecheck + lint + format:check + test + test:ui
Node floor: ≥ 20.19 (engines in package.json) — required by vite 7, which
builds the widget bundles. gen:ui runs automatically as a pre* hook of
dev, dev:http, typecheck, test, test:coverage and test:watch, so the
generated sources are never stale; you rarely call it by hand.
Testing
pnpm test # Server unit tests (1118 tests, 23 files) — node env
pnpm run test:ui # Widget tests under ui/ (436 tests, 10 files) — jsdom env
pnpm run test:watch # Run tests in watch mode
pnpm run test:coverage # Tests with V8 coverage report
pnpm run test:integration # Integration tests (separate config, requires network)
pnpm run test:host # Host-sim harness (Playwright, real Chromium iframes) — needs `pnpm exec playwright install chromium` once; not part of `check`/CI
Two separate vitest projects, because the widget needs a DOM and the server must
not have one: vitest.config.ts (node, excludes ui/**) and
vitest.ui.config.ts (jsdom, only ui/**/*.test.ts). pnpm run check runs
both.
The host-sim suite (tests/host-sim/, 25 specs in 4 files) is the third suite
and the only one outside vitest: Playwright mounts the built bundles in real
iframes and drives them with real clicks, against a hand-rolled stub of the
host side of the ext-apps postMessage protocol (host-stub.ts, injected via
page.evaluate). It is not in check, so its files reach the static gates by
other means — tests/tsconfig.json is a third tsc pass in typecheck, and
eslint/prettier target tests/ and the Playwright config. Playwright flags go
through pnpm exec playwright test --config playwright.host.config.ts <flags>;
pnpm run test:host -- <flags> swallows them silently. Host heights, host-call
latency and iframe click policies remain live-only findings; everything else —
scrolling, lazy loading, rail timing, latency feedback — belongs in this
harness (#95).
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.
- yesterday Changed · +4 lines · +114 tokens per session 80e66826ded0
- 5d ago Changed · +27 lines · +554 tokens per session 1b9c7614e91b
- 10d ago First seen · 755 lines · 11,563 tokens per session scan A 6dc35d58ce70
ris-mcp-ts CLAUDE.md is an instructions file published in the GitHub repository Honeyfield-Org/ris-mcp-ts (16 stars, last pushed 2d ago), licensed MIT. It adds 12,231 tokens to every session, about $0.0612 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.