What is emap-labs CLAUDE.md?

A project guide for emap-labs, a data and intelligence codebase connected to a production application. It documents related repositories, data pipelines, evaluation commands, deployment, and ethical rules.

Use it when running dataset pipelines, checking retrieval quality, refreshing evaluation data, deploying the semantic service, or working across emap-labs and emap-next.

It helps an agent understand which repository and environment to use, how data moves between projects, and which project policies must be followed.

How r3tr0eth/emap-labs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to r3tr0eth/emap-labs. 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/r3tr0eth/emap-labs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/r3tr0eth/emap-labs

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/r3tr0eth/emap-labs/claude-md/github.svg)](https://agentmods.dev/instructions/r3tr0eth/emap-labs/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/r3tr0eth/emap-labs/claude-md"><img src="https://agentmods.dev/badge/instructions/r3tr0eth/emap-labs/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/r3tr0eth/emap-labs/claude-md"><img src="https://agentmods.dev/badge/instructions/r3tr0eth/emap-labs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 958 This file is loaded in full into every session.

When invoked 958 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	$0.00958	$0.00958
Opus 5.5	$0.00383	$0.00383
Sonnet 5.5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash e66476896126, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

emap-labs 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — emap-labs

Capa de datos e inteligencia detrás de emap (github.com/r3tr0eth/emap-labs, público). Roadmap: docs/ROADMAP.md. Reglas duras: docs/ETICA-DATOS.md (infraestructura jamás personas) y la regla financiera: emap solo gasta dinero que emap trae.

Relación con otros repos

../emap-next: producto en producción (Vercel + VPS Hetzner). Sin remoto git — solo commits locales; deploy con vercel deploy --prod --yes.
Los pipelines de datasets/ escriben en emap-next/data/processed/ y se registran en su manifest (python -m data_catalog validate|quality|check con el venv de emap-next).

Comandos

../emap-next/.venv/bin/python evals/run.py [--retriever baseline|semantic|hybrid] \
    [--lang es|eu] [--split dev|heldout|all] [--min-pass N]   # evals
./evals/sync-data.sh              # refrescar snapshot para CI tras cambiar datos
../emap-next/.venv/bin/python datasets/<pipeline>/build.py    # pipelines
./service/deploy.sh               # desplegar servicio semántico al VPS
ssh [email protected]          # VPS (OTP :8082, semantic :8083, nginx)

Venv propio (.venv, python3.13: fastembed/numpy) solo para el retriever semántico; todo lo demás usa el venv de emap-next.
held-out (ho-*) jamás se usa para calibrar; si se mira para depurar, se promociona a dev y se escriben casos nuevos.
CI corre en cada push (.github/workflows/evals.yml) con gates --min-pass; si tocas retriever o corpus, actualiza los umbrales conscientemente en el mismo PR, nunca para "que pase".

Loops (convención de trabajo con Claude Code)

Regla previa: lo determinista va en scripts (cron del VPS o *.sh del repo), los bucles de agente son para juicio e iteración. Recetas:

Turn-based + verificación: cualquier cambio de retriever/corpus termina con evals/run.py en dev (ES y EU) antes de commitear; cambios de UI en emap-next, con la skill verify-frontend-change / QA CDP.
/goal con gate de eval (el mejor encaje: criterio determinista): /goal sube hybrid held-out EU a ≥75% sin bajar ES de 79% ni dev, máx 5 intentos — tocando solo dev para iterar; held-out se corre UNA vez al final.
/loop para CI: tras push con cambios de evals, /loop 5m mira el workflow evals de emap-labs y arregla si falla.
Proactivo (pendiente de activar, consume cuota — decidir Gaizka): rutina semanal sobre este repo: re-ejecutar pipelines con fetch remoto (neighborhoods/Overpass), sync-data.sh, evals completas, y abrir issue si hay drift de datos o caída de gates. Solo tiene sentido semanal — las fuentes no cambian más rápido.

Read the full file on GitHub · 65 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.

2mo ago First seen · 65 lines · 958 tokens per session scan A e66476896126

Subscribe to this mod's changes

emap-labs CLAUDE.md is an instructions file published in the GitHub repository r3tr0eth/emap-labs (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 958 tokens to every session, about $0.0038 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.

emap-labs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
emap-labs CLAUDE.mdr3tr0eth/emap-labs	Instructions file	0	2mo ago	Apache-2.0	A	958	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

emap-labs: Instructions file for Claude Code