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 | $0.02136 | $0.02136 |
| Opus 5.5 | $0.00854 | $0.00854 |
| Sonnet 5.5 | $0.00427 | $0.00427 |
| Haiku 4.5 | $0.00214 | $0.00214 |
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 6d 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 — 135 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 Standardize + the kernel (the library) | vocabulary: engine/, lexical.py, units/, value_scale.py, zh_fold.py, _bundle.py, _strtab.py; the pure seam: standardize/ (fold, parse, local_day, series, code, devices); semantics: kernel/ (metrics, series, quality, overlay, meds, query, tools, ops, connect, sink, events, evidence, memory, decoders/); toolbox: testing/ |
pip install mirobody (numpy only) |
each other, nothing else |
| ② Standardize, the parts that reach a database | standardize/aggregate/, standardize/derive/, standardize/indicators_info.py, standardize/canonical_units.py, standardize/value_range_validator.py |
[app] |
no agent framework |
| ① Collect + storage + MCP | mirobody/documents/, collect/, utils/, user/, task/, mcp/ |
[parse] / [app] |
no langchain*, langgraph, deepagents |
| ③ Agent | 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/ (seven tools: resolve_indicator,
convert_unit, normalize_unit, query_health_indicators, query_medications,
query_genetic_data, query_pharmacogenomics) —
and that list is asserted exactly by the local suite.
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).
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.
- 6d ago Changed 2346f4cd0679
- 6d ago Changed 013072965b8a
- 9d ago Changed · +14 tokens per session 5e3ccb4fc0a1
- 22d ago Changed · +7 tokens per session 10b516a30a0c
- 29d ago Changed 59bca151e615
- 1mo ago Changed 04063746e360
- 1mo ago Changed · +2 lines · +57 tokens per session 2a2882a0362d
- 1mo ago Changed · +1 lines · +12 tokens per session 0a4126bd253c
- 1mo ago Changed · +9 tokens per session f216f8d9fbe4
- 1mo ago First seen · 132 lines · 2,037 tokens per session scan A 08bc220d7338
mirobody AGENTS.md is an instructions file published in the GitHub repository thetahealth/mirobody (1,408 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,136 tokens to every session, about $0.0085 per session on Opus 5.5. 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.
mirobody AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mirobody AGENTS.mdthetahealth/mirobody | Instructions file | 1.4k | yesterday | Apache-2.0 | A | 2,136 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |