What is sift CLAUDE.md?

Instructions for Sift, a multi-source investigation server that cross-references public company, sanctions, court, property, ownership, leak, and identity records.

Use them to investigate companies and people, trace ownership links, check sanctions or politically exposed person records, search filings and court records, and create investigation reports or visualizations.

They explain what each source contains and what access it requires, making it easier to combine records without treating one database as complete on its own.

How mefos-lab/sift configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mefos-lab/sift. 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/mefos-lab/sift/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mefos-lab/sift

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/mefos-lab/sift/claude-md/github.svg)](https://agentmods.dev/instructions/mefos-lab/sift/claude-md)

Your own site

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

Per session 2,820 This file is loaded in full into every session.

When invoked 2,820 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	$0.02820	$0.02820
Opus 5.5	$0.01128	$0.01128
Sonnet 5.5	$0.00564	$0.00564
Haiku 4.5	$0.00282	$0.00282

Measured 2mo ago against content hash 927f26e762c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sift 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 2mo 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 · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sift — Multi-Source MCP Server

MCP server that cross-references 9 public data sources: ICIJ Offshore Leaks, OpenSanctions, GLEIF LEI Registry, SEC EDGAR, UK Companies House, CourtListener (US court records), OCCRP Aleph (investigative datasets), UK Land Registry (property transactions), and Wikidata (entity enrichment and PEP identification).

Structure

sift/ — MCP server, API clients, traversal engine, visualizer
.claude/skills/ — Investigation skill (slash command)
patterns/ — Documented offshore structure patterns (accumulated over investigations)
visualizations/ — D3 HTML template for interactive investigation visualizations
investigations/ — Generated investigation reports and visualizations

Data Sources

Source	Coverage	Auth
ICIJ Offshore Leaks	810K+ entities from 5 leak investigations	None
OpenSanctions	320+ sanctions lists, PEP databases, enforcement records	API key
GLEIF LEI Registry	Global corporate identifiers + ownership chains	None
SEC EDGAR	US public company filings, 10-K/10-Q/8-K/DEF 14A, amendments	User-Agent only
UK Companies House	UK company records, officers, PSC, insolvency, disqualifications	Free API key
CourtListener	US federal court records, opinions, bankruptcy (PACER/RECAP)	Free token
OCCRP Aleph	Investigative datasets, entity networks, leaked documents	Approved account required
UK Land Registry	Property transactions, price history, high-value purchases	None
Wikidata	Structured data on people, companies, political roles	None

Skill

One unified skill with modes:

/investigate <name>                          — full cross-reference (default)
/investigate <name> --trace                  — multi-hop network traversal
/investigate <name> --trace --depth 3        — deep network walk (3 hops)
/investigate <name> --patterns               — structural pattern analysis
/investigate <name> --compliance             — rigorous sanctions/PEP screening
/investigate <name> --monitor                — check for new sanctions listings
/investigate <name> --jurisdiction           — jurisdictional footprint
/investigate <name1>, <name2>                — find connections between subjects
/investigate <name1>, <name2>, <name3>, ...  — merged network, find shared links

Read the full file on GitHub · 292 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.

2mo ago First seen · 292 lines · 2,820 tokens per session scan A 927f26e762c6

Subscribe to this mod's changes

sift CLAUDE.md is an instructions file published in the GitHub repository mefos-lab/sift (6 stars, last pushed 2mo ago), licensed MIT. It adds 2,820 tokens to every session, about $0.0113 per session on Opus 5.5. 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.

Research

sift CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sift CLAUDE.mdmefos-lab/sift	Instructions file	6	2mo ago	MIT	A	2,820	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sift: Instructions file for Claude Code