Borrowing it
Nothing to install: this file belongs to LesVulture/regwatch-co. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LesVulture/regwatch-co/main/CLAUDE.mdgit clone --depth 1 https://github.com/LesVulture/regwatch-coWrote 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.
[](https://agentmods.dev/instructions/lesvulture/regwatch-co/claude-md)<a href="https://agentmods.dev/instructions/lesvulture/regwatch-co/claude-md"><img src="https://agentmods.dev/badge/instructions/lesvulture/regwatch-co/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.
<a href="https://agentmods.dev/instructions/lesvulture/regwatch-co/claude-md"><img src="https://agentmods.dev/badge/instructions/lesvulture/regwatch-co/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02524 | $0.02524 |
| Opus 5 | $0.01262 | $0.01262 |
| Sonnet 5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
regwatch-co 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
regwatch-co — Monitor normativo y legislativo colombiano
Motor de búsqueda y monitoreo de la normatividad y la actividad legislativa de Colombia, consultable desde el móvil, capaz de responder preguntas en lenguaje natural con cada afirmación anclada a fuente primaria con URL y fecha de captura. La tesis pide datos frescos desde fuentes oficiales. collect.yml está en main (merge del PR #1, 2026-08-22): el cron diario queda registrado en la rama por defecto. El secreto SUPABASE_DB_URL existe. No se afirma que una corrida de collect haya terminado bien hasta observarla. Ver docs/ESTADO.md.
As-built: docs/ESTADO.md y el README.md. Contrato de evidencia: GOVERNANCE.md. Plan histórico de construcción: PLAN-V2.md (no se reescribe el cuerpo). Si ESTADO y el plan discrepan sobre qué existe, manda ESTADO. Si discrepan sobre qué debe ser cierto de un dato, manda GOVERNANCE.
La regla que define el proyecto (CRÍTICA)
Ningún dato entra sin procedencia checkeable. No es una preferencia de estilo: es la tesis del producto y lo único que lo diferencia de lo que ya existe.
- Todo registro lleva URL de fuente primaria + fecha de captura.
- Jerarquía probatoria:
primaria > institucional > secundaria. El campo se declara, no se infiere. vigenteexige fuente primaria. Sin cadena de evidencia completa, la respuesta es literalmente «vigencia no confirmada con fuente primaria».- La incertidumbre se declara, nunca se rellena. Un
NULLhonesto vale más que una fecha plausible. - Nunca se guarda prosa editorial de terceros como registro. Se guarda el hecho, y la prosa se descarta (
PLAN-V2.md§5.2).
Prohibido inventar datos
No completes un campo porque «probablemente sea así». No infieras una fecha de vigencia. No supongas que un endpoint devuelve lo que su documentación dice. Ábrelo y compruébalo.
Precedente vivo, y por eso esta regla existe: en la investigación previa, el 15 % de lo que los especialistas reportaron resultó falso al auditarse — incluida una receta de scraping que devolvía cero filas, un endpoint que fallaba en silencio con HTTP 200, y una defensa contra un modo de fallo que no existe.
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.
- 8d ago First seen · 106 lines · 2,524 tokens per session scan A 2c84cbc5b79d
regwatch-co CLAUDE.md is an instructions file published in the GitHub repository LesVulture/regwatch-co (0 stars, last pushed 9d ago), licensed MIT. It adds 2,524 tokens to every session, about $0.0126 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.
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.
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.
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).
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).
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.
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.