Borrowing it
Nothing to install: this file belongs to sjmatta/gedcom-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/sjmatta/gedcom-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/sjmatta/gedcom-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/sjmatta/gedcom-mcp/claude-md)<a href="https://agentmods.dev/instructions/sjmatta/gedcom-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sjmatta/gedcom-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/sjmatta/gedcom-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sjmatta/gedcom-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 | $0.02393 | $0.02393 |
| Opus 5.5 | $0.00957 | $0.00957 |
| Sonnet 5.5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
gedcom-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 24d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
GEDCOM MCP Server — a Python FastMCP server that exposes a genealogy database (a GEDCOM file) to AI assistants over the Model Context Protocol. It parses the .ged once at startup, builds in-memory indexes, and layers evidence-preserving reads, hybrid semantic search, GIS search, opt-in versioned writes and a research ledger on top.
Interface v2.0 advertises 9 tools read-only, or 13 with writes enabled; about twenty specialized tools are discovered on demand. There are 6 MCP resources. Requires Python 3.14 (.python-version; torch has no 3.15 wheels yet). Production tree: ~20K individuals, served over authenticated HTTP to ChatGPT, where an always-on OpenAI Dot uses it. See API.md, WRITES.md, RESEARCH_TOOLS.md, SEMANTIC_SEARCH.md and deploy/README.md; they are the detailed references and should be kept current.
Layered Architecture
MCP surface mcp_tools.py (core reads + discoverable research), write_tools.py
(prepare/apply/maintain + research ledger), discovery.py (search_tools,
call_research_tool, prepare_change), mcp_resources.py, http.py (Access JWT gate)
Domain logic core, relationships, interface_reads, research_reads, research_gaps,
events, places, narrative, associates, sources, tree_audit, pruning
Retrieval semantic.py + retrieval.py (passages, BM25 + dense RRF, cross-encoder rerank);
spatial.py + geocoding.py (3-tier geocoding, proximity/bbox search)
Writes writes.py (TreeStore), revision_storage.py (SQLite, content-addressed,
immutable), editing/document/field_edits/structural_edits (lossless editor),
research_ledger.py (append-only hypotheses/evidence/verdicts), recovery.py
Indexes state.py: individuals, families, sources, repositories, places, surname,
birth-year, place and individual-place indexes; TREE_LOCK; HOME_PERSON_ID
Parsing parsing.py (ged4py) → models.py dataclasses; tree_projection.py rebuilds
detached indexes after a write
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.
- 24d ago Changed · -159 lines · -1,766 tokens per session 4ee5b7f93170
- 1mo ago Changed · -15 lines · -339 tokens per session 070189060b52
- 1mo ago Changed · +61 tokens per session 91d619c98fc2
- 2mo ago Changed · +107 lines · +2,566 tokens per session 98c8f827a10a
- 2mo ago First seen · 164 lines · 1,871 tokens per session scan A 8569b24a85a6
gedcom-mcp CLAUDE.md is an instructions file published in the GitHub repository sjmatta/gedcom-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 2,393 tokens to every session, about $0.0096 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.
gedcom-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gedcom-mcp CLAUDE.mdsjmatta/gedcom-mcp | Instructions file | 1 | 3d ago | MIT | A | 2,393 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | yesterday | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |