mcpanonimohealth AGENTS.md

mcpanonimohealth AGENTS.md is an instructions file for Codex, OpenCode from alexandreumatize/mcpanonimohealth. It costs 542 tokens per session, scanned A, original, Apache-2.0.

A set of Codex instructions for protecting clinical documents and patient information. It requires documents to be selected through a local interface and forbids analysing files attached directly to chat.

In plain words
What is it for?
Enforcing safe document handling in the mcpanonimohealth repository, including refusing native attachments and using local de-identification before analysis.
Why use it?
It reduces the risk of sending identifiable health information to the chat provider and clearly handles attachments that may already have been uploaded.

Instructions file for CodexOpenCode

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/alexandreumatize/mcpanonimohealth/agents-md
Clone the repo
git clone --depth 1 https://github.com/alexandreumatize/mcpanonimohealth

Made for: Codex, OpenCode.

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 mcpanonimohealth AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexandreumatize/mcpanonimohealth/agents-md.svg)](https://agentmods.dev/instructions/alexandreumatize/mcpanonimohealth/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/alexandreumatize/mcpanonimohealth/agents-md"><img src="https://agentmods.dev/badge/instructions/alexandreumatize/mcpanonimohealth/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 542 This file is loaded in full into every session.
When invoked 542 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 $0.00542 $0.00542
Opus 5 $0.00271 $0.00271
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 3d ago against content hash 68d5c83bb73f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpanonimohealth AGENTS.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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proteção obrigatória de documentos clínicos

Estas regras se aplicam a toda tarefa executada pelo Codex neste repositório.

Anexos nativos são proibidos

  • Se a mensagem do usuário contiver imagem, PDF, documento, texto clínico colado ou qualquer outro anexo que possa conter dados de paciente, não analise, descreva, transcreva, resuma, extraia nem repita seu conteúdo.
  • Não use visão, leitura de arquivos, terminal, OCR ou outra ferramenta para inspecionar esse anexo.
  • Responda apenas: “Este arquivo foi anexado diretamente ao chat e não será analisado. O envio ao provedor pode já ter ocorrido. Encerre esta conversa, remova o anexo conforme os controles do seu provedor e inicie uma nova tarefa sem anexos. Na nova tarefa, peça: ‘Use o mcpanonimohealth para abrir a interface local.’”
  • Não afirme que a recusa desfaz o upload ou impede retenção pelo provedor.

Único fluxo permitido

  1. Antes de qualquer ferramenta, diga: “Antes de continuar: não anexe, arraste, cole nem envie o documento por este chat. Vou abrir uma interface local no navegador. Escolha o arquivo somente nessa página. O original será processado no computador; apenas o texto desidentificado em PASS poderá seguir para análise.”
  2. Mostre esse aviso em todo novo fluxo com documento, mesmo que o usuário já conheça o sistema.
  3. Verifique o MCP mcpanonimohealth.
  4. Chame selecionar_e_desidentificar, que abrirá uma página dedicada em 127.0.0.1 e devolverá um job_id imediatamente.
  5. O médico escolhe o documento somente nessa página local.
  6. Não espere confirmação no chat (não peça “Feito” nem “avise quando terminar”). Chame consultar_job logo em seguida e repita a cada poucos segundos enquanto o estado for PROCESSING, até PASS, HOLD, ERROR ou EXPIRED. Cada chamada de ferramenta deve retornar rápido — não bloqueie uma tool esperando o médico na página.
  7. Somente em PASS, obtenha e analise o derivado (texto_desidentificado; em lote, itens[]) e organize a análise na conversa.
  8. Descarte o job ao terminar.

Read the full file on GitHub · 24 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.

  1. 3d ago First seen · 24 lines · 542 tokens per session scan A 68d5c83bb73f

Subscribe to this mod's changes

mcpanonimohealth AGENTS.md is an instructions file published in the GitHub repository alexandreumatize/mcpanonimohealth (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 542 tokens to every session, about $0.0027 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens