sovereignty-scan-mcp: Instructions file for Claude Code

CLAUDE.md

sovereignty-scan-mcp CLAUDE.md is an instructions file for Claude Code from mightbesaad/sovereignty-scan-mcp. It costs 3,510 tokens per session, scanned A, original, MIT.

A repository rulebook for sovereignty-scan-mcp, a tool that checks whether software vendors meet European Union AI Act requirements.

In plain words
What is it for?
It is for guiding coding agents through structural changes, data-model work, seeding data, and other non-trivial edits.
Why use it?
It prevents important project decisions and architecture from being changed without reading the documents that define them.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mightbesaad/sovereignty-scan-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mightbesaad/sovereignty-scan-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,510 This file is loaded in full into every session.
When invoked 3,510 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 $0.03510 $0.03510
Opus 5 $0.01755 $0.01755
Sonnet 5 $0.00702 $0.00702
Haiku 4.5 $0.00351 $0.00351

Measured 11d ago against content hash a00361d7970f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sovereignty-scan-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 11d 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 · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — @kajaril/sovereignty-scan-mcp

This file is the constitution for Claude Code working in this repo. Read it before any non-trivial change.

This is a template. Copy to the repo root as CLAUDE.md at milestone M1. Update the "Repo state" section as the build progresses. Everything above that section is locked and should not be edited without a corresponding decision update in kajaril-decisions-addendum-wk0.md or this plan.


What kajaril is

A one-person studio out of Cairo. Tools, agents, and platforms — built quietly, finished properly. This repo is the first published MCP product: a vendor sovereignty scanner for EU AI Act compliance.

The product is an artifact in a credential layer. Code shipped here will be read by DPO buyers, regulators, and audit agents. Every decision in this codebase is on the record.

Required reading before structural changes

Three documents are canonical. Read them, in order, before any change that touches architecture, the data model, the seed, or any locked decision:

  1. kajaril-source-of-truth.md — strategy, wedge, stack, roadmap
  2. kajaril-decisions-addendum-wk0.md — entity-level locked decisions #11–#18 (overrides §2.2 and §4.2 of the source-of-truth)
  3. sovereignty-scan-mcp-plan.md — Week 1 build plan + locked decisions #1–#7 specific to this MCP

These files live in the kajaril Entity folder, not in this repo. The build plan is the spec. Deviating from any locked decision (#1–#7 in the build plan, #11–#18 in the addendum) requires stopping, asking, and recording the new decision in writing before code changes.

Locked decisions for this repo

These are not negotiable. If implementation reveals a reason one should change, stop and ask — do not adapt the code to a different decision silently.

  1. Database split — Free-tier worker binds only to sovereignty_db_free. Never adds a binding to sovereignty_db_paid for any reason.
  2. scan_stack cap — Hard limit of 50 providers per call. Returns INPUT_TOO_LARGE over.
  3. suggest_eu_alternatives algorithm — Deterministic. The four-step logic in the build plan §Decisions is the spec; do not introduce ranking heuristics.
  4. Error envelope — Every failure path returns {error: {code, message, retryable, details}}. Codes are locked at v0.1.0; do not add new codes without updating types.ts first and bumping the contract.
  5. KV cache key strategy — Per-provider keys (provider:{id}, category:{name}:ids, all:provider_ids, meta:last_refresh). Do not switch to a snapshot-blob pattern.
  6. Provider data updatesseed.ts is the source of truth. D1 is derived. All updates are commits to seed.ts, reviewed via PR, then idempotent reseed (INSERT ... ON CONFLICT DO UPDATE). Writing SQL UPDATE directly against live D1 is prohibited — it leaves no audit trail.
  7. License + metadata — MIT. package.json author, repository, homepage, bugs are locked. LICENSE file at repo root.

Read the full file on GitHub · 201 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. 11d ago First seen · 201 lines · 3,510 tokens per session scan A a00361d7970f

Subscribe to this mod's changes

sovereignty-scan-mcp CLAUDE.md is an instructions file published in the GitHub repository mightbesaad/sovereignty-scan-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 3,510 tokens to every session, about $0.0175 per session on Opus 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

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens