OpenMed is local-first healthcare AI software that extracts clinical information and removes personally identifying details from clinical text on hardware controlled by the user. Healthcare developers use its Python runtime, Apple Silicon and mobile SDKs, and browser support for on-device clinical NER and PII de-identification.
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/maziyarpanahi/openmed/agents-mdgit clone --depth 1 https://github.com/maziyarpanahi/openmedWrote 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/maziyarpanahi/openmed/agents-md)<a href="https://agentmods.dev/instructions/maziyarpanahi/openmed/agents-md"><img src="https://agentmods.dev/badge/instructions/maziyarpanahi/openmed/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 5.1 | $0.01743 | $0.01743 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
openmed 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core Python package code lives in openmed/. Keep existing privacy and registry code in openmed/core/; add genuinely new capability in top-level packages already present or planned: clinical/, eval/, multimodal/, structured/, risk/, and interop/. Backend adapters live in mlx/, coreml/, and torch/; the REST surface is in service/; Swift code and demos are in swift/. Tests are under tests/unit, tests/integration, and tests/fixtures; docs are in docs/; examples are in examples/; release and maintenance scripts are in scripts/.
Build, Test, and Development Commands
uv pip install -e ".[dev]": install editable package with test and lint dependencies.uv pip install -e ".[dev,hf]": add Hugging Face dependencies for model-related work..venv/bin/python -m pytest tests/ -q: run the full test suite before preparing a PR.pytest --cov=openmed --cov-report=term-missing: run local coverage.make build: build wheel and sdist viapython3 -m build.make docs-serve/make docs-build: preview or strictly build MkDocs.cd swift/OpenMedKit && swift test: run Swift package tests.
Linting and Formatting
Use the checked-in tooling as the single source of truth. Do not apply ad hoc editor formatting or alternate lint configurations.
Python linting and formatting are owned by Ruff through pyproject.toml, .pre-commit-config.yaml, and the CI lint job. Before opening a Python-touching PR, run make format, make lint, and make format-check. Use pre-commit run --all-files for broad validation, or pre-commit run --files <paths> when validating a tightly scoped change.
Swift package formatting is separate from Python. OpenMedKit Swift code uses Apple swift-format through .swift-format, scripts/format_swift.sh, scripts/lint_swift.sh, and the Swift package CI workflow. Before opening a PR that touches Package.swift or swift/OpenMedKit, run make format-swift and make lint-swift.
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 First seen · 86 lines · 1,743 tokens per session scan A a682e6c46e6c
openmed AGENTS.md is an instructions file published in the GitHub repository maziyarpanahi/openmed (5,237 stars, last pushed today), licensed Apache-2.0. It adds 1,743 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 2026-08-30.
Other instructions, from other repositories
osaurus AGENTS.md
AGENTS.md instructions for osaurus-ai/osaurus, covering codex configuration - osaurus-staging, build & test, keychain tip (optional), osaurus release proof and pr reporting and model runtime non-negotiables.
vllm.cpp AGENTS.md
AGENTS.md instructions for mudler/vllm.cpp, covering agents.md: the rules, start here, history is git, every change starts from an issue and spec before code.
HealthChain CLAUDE.md
Claude Code instructions for healthchainai/HealthChain, covering healthchain - claude code context, 0. project overview, 1. non-negotiable golden rules, 2. testing discipline and 3. build, test & utility commands.
Logue CLAUDE.md
Claude Code instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.
Bonsai-demo AGENTS.md
AGENTS.md instructions for PrismML-Eng/Bonsai-demo, covering agent guide — tuning the bonsai demo, why the 27b models (what to show off), the models, knobs that matter (27b) and adding mcp servers.
douyin-agent-kit AGENTS.md
Instructions for liusencomic-cyber/douyin-agent-kit, covering agents.md — douyin-agent-kit, 项目概览, 仓库结构, 构建与运行 and 环境：python 3.10+（转录需 macos apple silicon + mlx-whisper）.