arcmap-mcp: Instructions file for Claude Code

CLAUDE.md

arcmap-mcp CLAUDE.md is an instructions file for Claude Code from pedralcg/arcmap-mcp. It costs 762 tokens per session, scanned A, original, MIT.

Project instructions for ArcMap MCP, a server that controls a running ArcMap 10.5 geographic information system. They describe its .NET add-in, Python server, branch rules, commit style, and test commands.

In plain words
What is it for?
They help maintain ArcMap integration code, follow GitHub Flow (branch and pull-request workflow), run Python 2.7 and 3 tests, and build the add-in.
Why use it?
They give an AI coding agent the project's structure and rules, reducing errors when changing or testing the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is pedralcg/arcmap-mcp's own configuration. It tells Claude Code how to work on arcmap-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything arcmap-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pedralcg/arcmap-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.

Copy the file
curl -O https://raw.githubusercontent.com/pedralcg/arcmap-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pedralcg/arcmap-mcp

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.

agentmods badge for arcmap-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pedralcg/arcmap-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/pedralcg/arcmap-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pedralcg/arcmap-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pedralcg/arcmap-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.

agentmods 80×15 button for arcmap-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pedralcg/arcmap-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pedralcg/arcmap-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 762 This file is loaded in full into every session.
When invoked 762 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00762 $0.00762
Opus 5.5 $0.00305 $0.00305
Sonnet 5.5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured yesterday against content hash a45ed459ba7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arcmap-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.

CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — arcmap-mcp

Servidor MCP que conduce un ArcMap 10.5 vivo. Dos piezas: el add-in .NET dentro de ArcMap (addin/, ArcObjects por CLR) y el servidor MCP en Python 3 (src/arcmap_mcp_server.py), que habla con el add-in por TCP en 127.0.0.1:27179. Los geoprocesos arcpy van fuera de proceso, con el Python 2.7 de ArcGIS (addin/ArcmapMcp.AddIn/Python/runner.py). La arquitectura y las herramientas están en README.md; la historia de cada versión, en CHANGELOG.md.

Flujo de ramas (GitHub Flow)

main es lo publicado y solo cambia por pull request con el CI en verde. La regla la impone GitHub (ruleset main protegida): PR obligatorio, check tests (py3 + py2.7) obligatorio y al día con main, sin force-push ni borrado. Sin revisores obligatorios: con un solo mantenedor nadie podría aprobar sus propios PR.

  1. git switch -c <tipo>/<tema> desde main actualizado (feat/…, fix/…, docs/…).
  2. Commits en Conventional Commits, en español.
  3. Antes de abrir el PR, en local:
    • python -m unittest discover -s tests con el venv del MCP (%LOCALAPPDATA%\arcmap-mcp\venv). Es lo mismo que corre el CI.
    • Si se toca el add-in: addin\build.ps1, instalar el .esriaddin, reiniciar ArcMap y pasar tests/regresion_sesion_viva.py (y regresion_ddp.py si toca exports o Data Driven Pages, y regresion_disco.py si toca edit_mxd_lote, compare_mxd o ArcmapMcp.Disco) contra ese ArcMap. Pegar el resumen en el PR. El CI no compila el C#: enlaza ArcObjects de Desktop 10.5, que no existe en un runner de GitHub.
  4. git push -u origin <rama> y gh pr create. Merge desde GitHub cuando el CI esté en verde (squash), y borrar la rama.
  5. Versiones: la versión vive en addin/ArcmapMcp.AddIn/Config.xml y en el .csproj (<Version>), más su entrada en CHANGELOG.md; se suben por PR. El tag (vX.Y.Z) se crea sobre main después del merge, nunca en una rama, y el release lleva el zip de empaquetar.ps1.

Read the full file on GitHub · 45 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.

  1. yesterday Changed · +1 lines · +33 tokens per session a45ed459ba7d
  2. 1mo ago First seen · 44 lines · 729 tokens per session scan A eef5dc2e3fab

Subscribe to this mod's changes

arcmap-mcp CLAUDE.md is an instructions file published in the GitHub repository pedralcg/arcmap-mcp (9 stars, last pushed yesterday), licensed MIT. It adds 762 tokens to every session, about $0.0030 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 2026-09-26.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens