What is Normativa-colombiana-MCP CLAUDE.md?

A project instruction file for Claude Code and its subagents working on a Colombian legal-information MCP project. It sets rules for choosing simple implementations, organizing source modules, replacing obsolete paths, and growing the project in stages.

Use it to guide implementation and subagent work in the Normativa-colombiana-MCP project, especially when changing data sources, adding regulators, or deciding how code should be structured.

It gives coding agents shared rules for making changes without preserving unnecessary old code or adding speculative complexity. It also records lessons from earlier project decisions.

How Angelthebestone/Normativa-colombiana-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Angelthebestone/Normativa-colombiana-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/Angelthebestone/Normativa-colombiana-MCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Angelthebestone/Normativa-colombiana-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/angelthebestone/normativa-colombiana-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/angelthebestone/normativa-colombiana-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/angelthebestone/normativa-colombiana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/angelthebestone/normativa-colombiana-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/angelthebestone/normativa-colombiana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/angelthebestone/normativa-colombiana-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,632 This file is loaded in full into every session.

When invoked 1,632 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.

Model	Per session	Once invoked
Fable 5.1	$0.01632	$0.01632
Opus 5.5	$0.00653	$0.00653
Sonnet 5.5	$0.00326	$0.00326
Haiku 4.5	$0.00163	$0.00163

Measured 29d ago against content hash 9d00fac6d62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Normativa-colombiana-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 29d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For any AI or human agent. This is law. Optimized for high-quality, maintainable, efficient systems in any language.

1. ARCHITECTURE & MODULARITY

The Golden Rule: Package by Feature, NEVER by Type.

FORBIDDEN: src/utils/, src/helpers/, src/common/, src/models/, src/controllers/, src/managers/. If you create utils, you failed to name the domain.
REQUIRED - Screaming Architecture: src/ billing/ # Business capability domain/ # Pure business logic, zero dependencies application/ # Use cases / Services infrastructure/ # DB, API clients, adapters presentation/ # HTTP handlers, CLI users/
Dependency Rule: domain -> knows nothing. application -> depends on domain ports. infrastructure -> implements ports. Dependencies point INWARD.
Principles: SOLID, High Cohesion / Low Coupling, Composition over Inheritance, Law of Demeter (no a.b().c().d()), Immutability by default.
File Size: Max 300 lines. One concept per file. If file needs And in its name, split it.
No God Objects, No Singletons with mutable state.

2. NAMING - Architecture is Naming

Folders = Business Nouns: orders/, payments/ GOOD. misc/ BAD.
Files = Domain Concepts: order_validator, payment_processor GOOD. helper, util, manager BAD.
Functions = Verbs + Intent: calculateTotalWithTax() GOOD. doCalc(), process(), handle() BAD.
Booleans = Questions: isPaid, hasAccess, canCheckout.
Constants: No magic numbers. if status == 2 FORBIDDEN. if status == OrderStatus.PAID REQUIRED.
Consistency: getUser OR fetchUser, never both. snake_case or camelCase per language, but consistent.

3. CODE QUALITY & ANTI-DRY

DRY - Zero Tolerance for Duplication: 3 lines duplicated twice = extract to domain function.
KISS & YAGNI: Don't abstract prematurely. Don't build for "future". Simplest solution that satisfies behavior wins.
Functions: Max 3 params (else use DTO), Max 1 indent level (use guard clauses if !valid { return err }), Cyclomatic Complexity < 10.
No else hell, no nested loops > 2 levels.

Read the full file on GitHub · 105 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.

29d ago Changed · +23 lines · -391 tokens per session 9d00fac6d62c
2mo ago First seen · 82 lines · 2,023 tokens per session scan A ef8b7190c4a8

Subscribe to this mod's changes

Normativa-colombiana-MCP CLAUDE.md is an instructions file published in the GitHub repository Angelthebestone/Normativa-colombiana-MCP (6 stars, last pushed 15d ago), licensed Apache-2.0. It adds 1,632 tokens to every session, about $0.0065 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.

Legal and compliance claude colombia derecho jurisprudencia legaltech

Normativa-colombiana-MCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Normativa-colombiana-MCP CLAUDE.mdAngelthebestone/Normativa-colombiana-MCP	Instructions file	6	15d ago	Apache-2.0	A	1,632	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

Normativa-colombiana-MCP: Instructions file for Claude Code