mcp-archimate: Instructions file for Claude Code

CLAUDE.md

mcp-archimate CLAUDE.md is an instructions file for Claude Code from lacrif/mcp-archimate. It costs 1,115 tokens per session, scanned A, original, MIT.

A project instruction file for mcp-archimate, covering task tracking, release notes, tests, coverage, and validation of ArchiMate XML files.

In plain words
What is it for?
Use it when changing code, preparing releases, checking coverage, or verifying XML files with Archi.
Why use it?
It gives contributors a repeatable checklist for keeping project records, test quality, and architecture files consistent.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is lacrif/mcp-archimate's own configuration. It tells Claude Code how to work on mcp-archimate 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 mcp-archimate configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lacrif/mcp-archimate. 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/lacrif/mcp-archimate/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lacrif/mcp-archimate

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 mcp-archimate CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lacrif/mcp-archimate/claude-md"><img src="https://agentmods.dev/badge/instructions/lacrif/mcp-archimate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,115 This file is loaded in full into every session.
When invoked 1,115 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 $0.01115 $0.01115
Opus 5.5 $0.00446 $0.00446
Sonnet 5.5 $0.00223 $0.00223
Haiku 4.5 $0.00112 $0.00112

Measured 2mo ago against content hash 9af1bf8373db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-archimate 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Instructions

Task backlog and release notes

  • The TODO.md file centralizes all ongoing tasks for new releases. Before starting a task, review it: select an item or add one if necessary.
  • Once a task is complete, check the corresponding box in TODO.md.
  • When a release is ready, move the checked items from TODO.md to CHANGELOG.md.
  • Write concise and clear changelog entries (describe the changes, not the method). One bullet point per change.
  • When tagging a release (e.g. git tag 0.4.0), bump package.json "version" to match, run npm test, commit the bump, then create the tag and push both: git push origin main --tags.

After every code change

  1. Run the tests: npm test — all tests must pass before considering the change done.
  2. Check coverage: npm test -- --coverage — line/branch/function coverage must stay at or above 80%. If a change drops coverage below 80%, add tests before finishing.
  3. Validate the .xml file: after any write/save operation, verify the file is valid by importing it with Archi:
    archi -application com.archimatetool.commandline.app -consoleLog -nosplash --xmlexchange.import "data/archisurance.xml"
    
    A successful [XML Exchange] Validated! + [XML Exchange] XML Imported! confirms the file is well-formed and conforms to the Open Exchange XSDs in models/. Cascade-deletes already strip dangling view nodes; identifiers generated by mutation handlers are prefixed with id- to satisfy the xs:ID / NCName constraint.
  4. Update the documentation: keep README.md in sync with any API, MCP tool, or behaviour change.

Image export conventions

  • SVG/PNG exports: all view exports (SVG and PNG) go to exports/views/. Never write generated images to public/images/views/ or any other directory.
  • Reference SVGs: exports/references/ contains SVGs exported directly by the Archi tool — these are the ground truth. When improving the renderer (src/renderer.ts), compare generated output against the matching file in exports/references/ and minimize visual differences (shapes, colors, layout, connectors, labels, fonts).

Read the full file on GitHub · 57 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. 2mo ago First seen · 57 lines · 1,115 tokens per session scan A 9af1bf8373db

Subscribe to this mod's changes

mcp-archimate CLAUDE.md is an instructions file published in the GitHub repository lacrif/mcp-archimate (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0045 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.

Related

mcp-archimate CLAUDE.md compared with instructions from other repositories

mcp-archimate CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-archimate CLAUDE.mdlacrif/mcp-archimateInstructions file05mo agoMITA1,115Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode