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.
npx agentmods add instructions/anfaia/climasafe/claude-mdgit clone --depth 1 https://github.com/ANFAIA/ClimaSafeWrote 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/anfaia/climasafe/claude-md)<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>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 | $0.00494 | $0.00494 |
| Opus 5 | $0.00247 | $0.00247 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
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.
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
- Ejecuta
./init.shantes de tocar nada. Si saleENTORNO BLOQUEADO, para y repórtalo. No se implementa encima de un proyecto roto. - Ninguna feature se cierra sin la puerta en verde y evidencia real.
Lo aplica
harness finishen código: rechaza siinit.shfalla o si no le pasas la salida del comando que lo demuestra. - No edites
featureslist.jsonniprogress/a mano. Su dueño es el agenteharness.
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.
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.
- 5d ago First seen · 44 lines · 494 tokens per session scan A 7241d2449f73
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.
Other instructions, from other repositories
Kokoro-FastAPI AGENTS.md
AGENTS.md instructions for remsky/Kokoro-FastAPI, covering agents.md, layout, commands, conventions and gotchas.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
cpf-validador CLAUDE.md
Claude Code instructions for opastorello/cpf-validador, covering claude.md, comandos, rodar localmente (fastapi + fastmcp na porta 8000), docker (porta 8002 conforme docker-compose.yaml) and arquitetura.
Huntable-CTI-Studio AGENTS.md
AGENTS.md instructions for dfirtnt/Huntable-CTI-Studio, covering agents.md, orientation, local context, prompt-injection alerting and change-type quick reference.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.