OpenELIS-Global-2 copilot-instructions.md

OpenELIS-Global-2 copilot-instructions.md is an instructions file for GitHub Copilot from DIGI-UW/OpenELIS-Global-2. It costs 3,023 tokens per session, scanned A, original, MPL-2.0.

Code-review instructions for OpenELIS Global 2, a healthcare laboratory information system. They define checks for safety, security, workflows, architecture, testing, and AI-generated code.

In plain words
What is it for?
Use them to review authentication, permissions, database changes, laboratory results, FHIR data exchange, shared services, and other sensitive changes.
Why use it?
Healthcare software can cause serious problems when data, permissions, or laboratory workflows are wrong. These instructions help reviewers identify high-risk defects and give actionable feedback.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions AGENTS.md.

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/digi-uw/openelis-global-2/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2

Made for: GitHub Copilot.

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 OpenELIS-Global-2 copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/digi-uw/openelis-global-2/copilot-instructions.svg)](https://agentmods.dev/instructions/digi-uw/openelis-global-2/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/digi-uw/openelis-global-2/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/digi-uw/openelis-global-2/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,023 This file is loaded in full into every session.
When invoked 3,023 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 5.1 $0.03023 $0.03023
Opus 5 $0.01511 $0.01511
Sonnet 5 $0.00605 $0.00605
Haiku 4.5 $0.00302 $0.00302

Measured 6d ago against content hash f967e1bfd982, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

OpenELIS-Global-2 copilot-instructions.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.

.github/copilot-instructions.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenELIS Global 2 — Copilot Code Review Instructions

Purpose

  • Review changes for constitutional compliance, workflow impact, testing/validation quality, manageable scope, and AI-generated artifacts.
  • This repository is a mission-critical healthcare LIMS. Prefer correctness, safety, and maintainability over speed.
  • Inline rules here are the minimum bar. For details, see:
    • .specify/memory/constitution.md
    • .specify/guides/testing-roadmap.md
    • AGENTS.md
    • PULL_REQUEST_TIPS.md

Review priorities

  • Blockers first: security, data integrity, broken workflows, and architecture violations.
  • High-risk changes: authentication/authorization, analyzer interfaces, results reporting, database migrations, FHIR sync, and shared utility/service code.
  • Prefer actionable feedback: point to the risky file/pattern, explain impact, suggest a concrete alternative.

Security critical issues

  • Check for hardcoded secrets, API keys, or credentials.
  • Verify RBAC / authorization checks exist for sensitive operations.
  • Flag missing input validation or sanitization (XSS, SQL injection, path traversal).
  • Review authentication and session-handling changes carefully.
  • Ensure audit logging requirements are respected for data-changing operations.

Code quality essentials

  • Functions should be focused and appropriately sized.
  • Use clear, descriptive naming; avoid magic numbers/strings.
  • Ensure proper error handling—no empty catch blocks or swallowed exceptions without explanation.
  • Remove dead code, commented-out blocks, and unused imports.

Constitutional compliance (9 principles)

I. Configuration-driven variation (no country forks)

  • Flag any country-specific branching in code paths.
  • Prefer configuration-driven behavior via the existing configuration systems (e.g., SystemConfiguration, localization/config properties) rather than conditionals.

Examples

// BAD: country-specific branch in code
if ("MG".equals(countryCode)) {
    // Madagascar-only logic
}

// GOOD: read behavior from configuration (follow existing config patterns in the repo)
// String mode = configService.getValue("feature.mode");

Read the full file on GitHub · 397 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. 6d ago First seen · 397 lines · 3,023 tokens per session scan A f967e1bfd982

Subscribe to this mod's changes

OpenELIS-Global-2 copilot-instructions.md is an instructions file published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed today), licensed MPL-2.0. It adds 3,023 tokens to every session, about $0.0151 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.