ClimaSafe CLAUDE.md

ClimaSafe CLAUDE.md is an instructions file for coding agents from ANFAIA/ClimaSafe. It costs 494 tokens per session, scanned A, original, Apache-2.0.

Un conjunto de instrucciones para agentes de programación que trabajan en el proyecto ClimaSafeAI. Define comprobaciones, límites de edición, flujo de trabajo y funciones de varios subagentes.

In plain words
What is it for?
Sirve para preparar el entorno, consultar qué tarea toca, comprobar si se puede trabajar, delegar investigación e implementación y sincronizar las instrucciones de los asistentes.
Why use it?
Reduce el riesgo de trabajar sobre un entorno roto, modificar archivos que tienen otro dueño o cerrar una función sin pruebas y evidencias.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/anfaia/climasafe/claude-md
Clone the repo
git clone --depth 1 https://github.com/ANFAIA/ClimaSafe

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 ClimaSafe CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anfaia/climasafe/claude-md.svg)](https://agentmods.dev/instructions/anfaia/climasafe/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anfaia/climasafe/claude-md"><img src="https://agentmods.dev/badge/instructions/anfaia/climasafe/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 494 This file is loaded in full into every session.
When invoked 494 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00494 $0.00494
Opus 5 $0.00247 $0.00247
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 5d ago against content hash 7241d2449f73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ClimaSafe 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 5d 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 · 44 lines

What it actually says

ClimaSafeAI

Las reglas de este proyecto viven en AGENTS.md — el estándar que comparten todos los asistentes. Este fichero solo existe porque Claude Code lee CLAUDE.md; no dupliques nada aquí, o las dos copias divergirán.

@AGENTS.md

Lo mínimo que no puedes saltarte

  1. Ejecuta ./init.sh antes de tocar nada. Si sale ENTORNO BLOQUEADO, para y repórtalo. No se implementa encima de un proyecto roto.
  2. Ninguna feature se cierra sin la puerta en verde y evidencia real. Lo aplica harness finish en código: rechaza si init.sh falla o si no le pasas la salida del comando que lo demuestra.
  3. No edites featureslist.json ni progress/ a mano. Su dueño es el agente harness.
uv run python -m agents --json run harness next     # ¿qué toca?
uv run python -m agents --json run harness gate     # ¿se puede trabajar?
uv run python -m agents --json ask "<lo que sea>"   # ruteo automático

Subagentes

En .claude/agents/: lider (dirige el ciclo), explorer (investiga en solo lectura), implementer (escribe código y tests), reviewer (aprueba o rechaza). Se generan desde .opencode/agents/ con make assistants-sync, así que no los edites en .claude/ — se sobrescriben. Edita el original.

Commits

Solo cuando se pidan explícitamente, y los hace el agente git:

uv run python -m agents --json run git suggest_commit_message
uv run python -m agents --json run git commit_with_changelog --message "<msg>"

Conventional Commits (feat:, fix:, chore:, docs:, refactor:) y sin línea de co-autoría ni pie de ninguna herramienta de IA — el historial es del humano. No ejecutes git ni gh por iniciativa propia.

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. 5d ago First seen · 44 lines · 494 tokens per session scan A 7241d2449f73

Subscribe to this mod's changes

ClimaSafe CLAUDE.md is an instructions file published in the GitHub repository ANFAIA/ClimaSafe (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 494 tokens to every session, about $0.0025 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.