agentmods.dev

kontor-mcp: Instructions file for Claude Code

CLAUDE.md

kontor-mcp CLAUDE.md is an instructions file for Claude Code from DashankaNadeeshanDeSilva/kontor-mcp. It costs 313 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Kontor MCP, an offline tool for validating European electronic invoices and handling ZUGFeRD documents, a German invoice format.

In plain words
What is it for?
Use them when developing or changing the invoice validator and client, including rules, XML handling, money calculations, tests, and release notes.
Why use it?
They set rules for invoice accuracy, secure XML parsing, no network access, strict tests, structured tool data, and project documentation.

Instructions file for Claude Code

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

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

not rated 0repo 2mo ago A scan 313 tokens original Apache-2.0
View source ↗ DashankaNadeeshanDeSilva/kontor-mcp
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dashankanadeeshandesilva/kontor-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dashankanadeeshandesilva/kontor-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 313 This file is loaded in full into every session.
When invoked 313 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 $0.00313 $0.00313
Opus 5.5 $0.00125 $0.00125
Sonnet 5.5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 2mo ago against content hash 704e63cda81c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kontor-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 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 · 12 lines

What it actually says

Kontor MCP — project context for Claude Code

  • Read docs/PRD.md (scope, tool specs §5.5, NFRs §6) and docs/IMPLEMENTATION_PLAN.md (current phase) before coding.
  • Monorepo: pnpm workspaces. Node >= 20, TypeScript strict. Test runner: vitest. Run pnpm -r test before claiming done.
  • Money math: decimal.js only — never float. XML parsing: XXE disabled everywhere (see NFR-5).
  • Never introduce a runtime network call. The no-network test (packages/core/test/sovereignty.test.ts) must always pass.
  • All MCP tool inputs/outputs: Zod schemas; tools return structuredContent + text summary; findings use the Finding interface (PRD §5.2).
  • Rule namespaces: official rules keep their IDs (BR-, BR-DE-); our own checks are KONTOR-PLAUS-*.
  • When touching packages/rules artifacts: update PROVENANCE.md (source, version, date, license, sha256).
  • Conventional commits. Update CHANGELOG.md per user-visible change.
  • npm scope is @kontor-mcp/* (decided 2026-08-25, see docs/DECISIONS.md). Verify library versions/APIs against live docs before use; log choices in docs/DECISIONS.md.
  • macOS FS is case-insensitive: never create paths differing only by case (docs vs Docs).
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 · 12 lines · 313 tokens per session scan A 704e63cda81c

Subscribe to this mod's changes

kontor-mcp CLAUDE.md is an instructions file published in the GitHub repository DashankaNadeeshanDeSilva/kontor-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 313 tokens to every session, about $0.0013 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.

Finance and fintechLegal and compliance
Related

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

kontor-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kontor-mcp CLAUDE.mdDashankaNadeeshanDeSilva/kontor-mcpInstructions file02mo agoApache-2.0A313Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode