Borrowing it
Nothing to install: this file belongs to paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/claude-md)<a href="https://agentmods.dev/instructions/paulieb89/uk-legal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paulieb89/uk-legal-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 | $0.03785 | $0.03785 |
| Opus 5 | $0.01893 | $0.01893 |
| Sonnet 5 | $0.00757 | $0.00757 |
| Haiku 4.5 | $0.00379 | $0.00379 |
Grade A, and why
uk-legal-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 7d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — uk-legal-mcp
What this is
UK legal research MCP server. Eight namespaced modules (case_law, legislation, parliament, bills, votes, committees, citations, hmrc) plus gateway companion + resource-bridge tools, mounted into a single FastMCP v3 gateway. For the live tool count run fastmcp inspect or len(await client.list_tools()) — don't hardcode it (Obs 217). Deployed to Fly.io (London region). Streamable HTTP transport.
Live endpoint: https://uk-legal-mcp.fly.dev/mcp
Repo: https://github.com/paulieb89/uk-legal-mcp
Client ecosystems served
Per the May 2026 dogfeed audit, four MCP-speaking client ecosystems are in scope:
| Ecosystem | Audience | MCP capabilities used | Workflow distribution |
|---|---|---|---|
| ChatGPT consumer | ~80M/week, casual UK legal lookups | TOOLS ONLY — no resources, prompts, sampling, elicitation, skills | Tool descriptions are the only layer |
| Claude Code | Developer + lawyer-developers | Tools + resources + prompts + skills (via .claude-plugin/) |
Tool descriptions + skills in uk-legal-plugins |
| Cowork | Anthropic collab env | Same as Claude Code | Same as Claude Code |
| OpenAI Codex CLI | OpenAI developer audience | Tools + resources + prompts + skills (via .codex-plugin/) |
Tool descriptions + skills (dual-manifest plugins) |
Critical: tool descriptions are LOAD-BEARING for the ChatGPT cohort. The 4-part description pattern (USE WHEN / what it returns / AFTER calling / authoritative-source clause) is mandatory for any new or modified tool. See docs/internal/chatgpt-workflow-encoding.md.
Documentation index
Public docs ship in docs/ (api-reference.md, lawyer-guide.md, tool-reference.md). Internal working notes live in docs/internal/ — gitignored, local-only, not in the public repo:
docs/internal/chatgpt-workflow-encoding.md— how to encode workflow knowledge in tool descriptions when skills aren't reachable; 4-part pattern + 4 worked examplesdocs/internal/handover.md,docs/internal/post-0.5.0-backlog.md— session handover + tracked backlogdocs/internal/releasing.md— maintainer release procedure
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.
- 7d ago Changed · -1 lines · +201 tokens per session da92c5a6409c
- 12d ago First seen · 190 lines · 3,584 tokens per session scan A 1d6703244fd3
uk-legal-mcp CLAUDE.md is an instructions file published in the GitHub repository paulieb89/uk-legal-mcp (16 stars, last pushed today), licensed MIT. It adds 3,785 tokens to every session, about $0.0189 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
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.
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).
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.
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).