rootcause-mcp AGENTS.md

rootcause-mcp AGENTS.md is an instructions file for Codex, OpenCode from u9401066/rootcause-mcp. It costs 1,742 tokens per session, scanned A, original, Apache-2.0.

Workspace instructions for building RootCause MCP, a clinical reasoning tool that examines multiple de-identified medical records. They define how to produce an evidence-linked diagnosis analysis and keep human review in control.

In plain words
What is it for?
Following a required workflow for timelines, competing diagnoses, evidence links, cognitive checks, cause analysis, limitations, and clinician review.
Why use it?
It keeps medical reasoning traceable and cautious by separating recorded facts from interpretations and possible causes. It also prevents the tool from being treated as an autonomous diagnosis or treatment system.

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/u9401066/rootcause-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/u9401066/rootcause-mcp

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 rootcause-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/u9401066/rootcause-mcp/agents-md.svg)](https://agentmods.dev/instructions/u9401066/rootcause-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/u9401066/rootcause-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/u9401066/rootcause-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,742 This file is loaded in full into every session.
When invoked 1,742 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 $0.01742 $0.01742
Opus 5 $0.00871 $0.00871
Sonnet 5 $0.00348 $0.00348
Haiku 4.5 $0.00174 $0.00174

Measured 3d ago against content hash 778d0106eae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rootcause-mcp 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.

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RootCause MCP Clinical Reasoning Harness

These are the workspace instructions for agents developing or using RootCause MCP to turn multiple de-identified clinical records into an evidence-grounded differential diagnosis and medical root-cause analysis.

Goal

Produce one auditable case package with source lineage, canonical timeline, competing DDx, Bayesian evidence links, cognitive audit, Fishbone/Why/HFACS analysis, conservative causation status, limitations, and qualified-human review state.

Working style

  • Use Traditional Chinese unless the user requests another language.
  • For clinician-facing prose, keep canonical diagnosis, test, drug, and procedure names in English. On first use, an established abbreviation may be written with an optional Traditional Chinese gloss; never invent a translation or expand an ambiguous abbreviation.
  • Treat the system as retrospective decision support, never an autonomous diagnostic or treatment system.
  • Separate source observations, host extraction, clinical interpretation, hypotheses, and causal claims.
  • Treat unknown, unverified, and insufficient data as reasoning inputs: state which mechanisms remain open and what evidence would discriminate them instead of turning missingness into a negative finding.
  • Never fabricate a probability or likelihood ratio. An uncalibrated compatibility default is an implementation placeholder, not clinical probability, rank, or certainty.
  • Keep updates concise and state which workflow gate is complete or blocked.

Required harness

For case analysis, handoff, prompt/resource design, or agent integration, read:

  • .codex/skills/rootcause-clinical-reasoning-harness/SKILL.md
  • .codex/skills/rootcause-clinical-reasoning-harness/references/case-handoff.md
  • .codex/skills/rootcause-clinical-reasoning-harness/references/clinician-ddx-discussion-zh-tw.md when writing a clinician-facing DDx discussion
  • clinical://contracts/case-input-manifest
  • clinical://contracts/case-analysis-report

Read the full file on GitHub · 92 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 · 92 lines · 1,742 tokens per session scan A 778d0106eae4

Subscribe to this mod's changes

rootcause-mcp AGENTS.md is an instructions file published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 15d ago), licensed Apache-2.0. It adds 1,742 tokens to every session, about $0.0087 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.