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/u9401066/rootcause-mcp/agents-mdgit clone --depth 1 https://github.com/u9401066/rootcause-mcpWrote 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/u9401066/rootcause-mcp/agents-md)<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>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 | $0.01742 | $0.01742 |
| Opus 5 | $0.00871 | $0.00871 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
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.
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, andinsufficient dataas 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.mdwhen writing a clinician-facing DDx discussionclinical://contracts/case-input-manifestclinical://contracts/case-analysis-report
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.
- 3d ago First seen · 92 lines · 1,742 tokens per session scan A 778d0106eae4
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.
Other instructions, from other repositories
medical-calc-mcp copilot-instructions.md
Instructions for u9401066/medical-calc-mcp, covering copilot instructions for medical calculator mcp, 📊 專案概況, 🛠️ 開發環境, 安裝依賴 and 執行測試.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.
ai4science-studio CLAUDE.md
Instructions for AMDResearch/ai4science-studio, covering claude.md, repository purpose, agent entry points (read these first), directory layout and model slug rule.
leanforge-mcp CLAUDE.md
Claude Code instructions for sandraschi/leanforge-mcp, covering claude.md -- leanforge-mcp, what this repo does, key concepts, when working on agent.py and when working on leanclient.py.
orphanet-link CLAUDE.md
Claude Code instructions for berntpopp/orphanet-link, covering claude.md, essentials and common commands.
genefoundry-router CLAUDE.md
Instructions for berntpopp/genefoundry-router, a project described as: MCP gateway federating 21 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.