Borrowing it
Nothing to install: this file belongs to paulieb89/uk-due-diligence-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-due-diligence-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/paulieb89/uk-due-diligence-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-due-diligence-mcp/claude-md)<a href="https://agentmods.dev/instructions/paulieb89/uk-due-diligence-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paulieb89/uk-due-diligence-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-due-diligence-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paulieb89/uk-due-diligence-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 | $0.01047 | $0.01047 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
uk-due-diligence-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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uk-due-diligence-mcp
FastMCP server over 5 UK registers — Companies House, Charity Commission,
The Gazette, HMLR Land Registry, and OFSI/OFAC/EU/UN sanctions.
18 tools. Flat layout: server.py registers 8 domain modules.
- GitHub:
paulieb89/uk-due-diligence-mcp - Prod:
https://uk-due-diligence-mcp.fly.dev/mcp - Staging:
https://uk-due-diligence-mcp-staging.fly.dev(auto-deploys on push to main)
Not to be confused with
uk-business-mcp — a sibling repo in the same fleet directory, deployed at
uk-business-mcp.fly.dev/mcp — is the Ledgerhall proxy. It mounts this server
plus govuk-mcp, uk-legal-mcp and property-shared behind one URL, and has no
domain tools of its own. An unqualified "uk-business-mcp" almost always means that
proxy, not this server.
Releasing
Releases are GitHub-release-triggered, not tag-triggered: release.yml runs
on: release: published → PyPI → flyctl deploy. Pushing a tag alone publishes
nothing, and a hand-run fly deploy ships prod while silently skipping the PyPI
publish. Push to main deploys staging only.
A hand-run fly deploy is refused by .claude/hooks/pre_bash_deploy.py. A
deliberate rollback re-runs it with FLY_DEPLOY_ACK=1, which downgrades the
refusal to a confirmation prompt — it does not wave the command through, because
an agent reads the refusal and could otherwise set the variable itself.
Bumping a version means editing three files or the registries drift (this has
happened — see daaa9dc, and again at v1.3.0):
pyproject.toml, server.py (smithery_server_card), server.json (×2).
The version triad is asserted mechanically — see Invariants below — and
release.yml additionally checks it against the release tag, so neither a bump
that misses a file nor a tag that outruns the files can reach PyPI.
Run scripts/check-deploy-drift.sh to confirm what is actually running in prod
was built by CI from the latest release tag. Prod is release-gated, so main
running ahead between releases is normal — the script reports that distance as
information and still exits 0.
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 · +12 lines · +149 tokens per session dec85de03487
- 2d ago Changed · +5 lines · +80 tokens per session 32db56920778
- 3d ago Changed · +40 lines · +541 tokens per session 4e9c04ceccb8
- 11d ago First seen · 21 lines · 277 tokens per session scan A f70891458b44
uk-due-diligence-mcp CLAUDE.md is an instructions file published in the GitHub repository paulieb89/uk-due-diligence-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 1,047 tokens to every session, about $0.0052 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.
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.
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).