Mirobody is a health data engine that collects information from labs, wearables, genomics, imaging, and other sources, then standardizes it for AI use. It supports health applications and agents that answer questions about a person’s medical data with charts and citations. The catalogue skill extends interaction with this engine.
Borrowing it
Nothing to install: this file belongs to thetahealth/mirobody. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thetahealth/mirobody/main/AGENTS.mdgit clone --depth 1 https://github.com/thetahealth/mirobodyWrote 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/thetahealth/mirobody/agents-md)<a href="https://agentmods.dev/instructions/thetahealth/mirobody/agents-md"><img src="https://agentmods.dev/badge/instructions/thetahealth/mirobody/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/thetahealth/mirobody/agents-md"><img src="https://agentmods.dev/badge/instructions/thetahealth/mirobody/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01984 | $0.01984 |
| Opus 5 | $0.00992 | $0.00992 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
mirobody 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Mirobody with a coding agent
Read this before touching the tree. It is the short version of CONTRIBUTING.md plus the things an agent gets wrong first.
What this is
A Python 3.12+ health-data engine in three layers, and the layering is
machine-checked (lint-imports, contracts in pyproject.toml):
| Layer | Where | Installs with | May import |
|---|---|---|---|
| ② Translate + the kernel (the library) | vocabulary: engine.py, lexical.py, units/, value_scale.py, zh_fold.py, _bundle.py, _strtab.py; semantics: kernel/ (metrics, series, quality, overlay, meds, query, tools, ops, connect, sink, events, evidence, memory, vendors/); toolbox: testing/ |
pip install mirobody (numpy only) |
each other, nothing else |
| ① Collect + storage + MCP | mirobody/documents/, pulse/, indicator/, utils/, user/, task/, mcp/ |
[parse] / [app] |
no langchain*, langgraph, deepagents |
| ③ Answer | mirobody/agent/ (one agent: MirobodyAgent, on deepagents), server/ |
[agent] (the harness as a library) / [app] |
anything |
There is one agent, and it is not switched at request time. BaseAgent,
the agent/base package and the ChatGPT Apps widgets under agent/resources
were removed; do not reintroduce a second harness or a per-agent config
suffix. A deployment that wants its own harness REPLACES MirobodyAgent by
pointing AGENT_DIRS at its own directory (agent/registry.py). External
clients get the engine through mirobody/mcp/ (six tools: resolve_indicator,
convert_unit, normalize_unit, query_health_indicators, query_medications,
get_genetic_data) —
and that list is asserted exactly, in tests/agent/test_tool_surface.py.
The agent's config keys are MODELS, PROMPTS, ALLOWED_TOOLS,
DISALLOWED_TOOLS, DEFAULT_MODEL, AGENT_NAME — no suffix, and no "provider"
(in this project a provider is a device; PROVIDERS was the 1.4.0 spelling).
Setup that actually works from a source clone
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.
- today Changed · +1 lines · +28 tokens per session 2c1d05b33e75
- 2d ago Changed · -1 tokens per session d655fc83a7c3
- 5d ago First seen · 131 lines · 1,957 tokens per session scan A 31bb72ff2a2f
mirobody AGENTS.md is an instructions file published in the GitHub repository thetahealth/mirobody (1,298 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,984 tokens to every session, about $0.0099 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 2026-09-07.
Other instructions, from other repositories
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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.
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).