Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/digi-uw/openelis-global-2/agents-md)<a href="https://agentmods.dev/instructions/digi-uw/openelis-global-2/agents-md"><img src="https://agentmods.dev/badge/instructions/digi-uw/openelis-global-2/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 | $0.19053 | $0.19053 |
| Opus 5 | $0.09527 | $0.09527 |
| Sonnet 5 | $0.03811 | $0.03811 |
| Haiku 4.5 | $0.01905 | $0.01905 |
Grade A, and why
OpenELIS-Global-2 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 — 2,335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - README for AI Coding Agents
FILE Ownership Model (014 Remediation)
For FILE-based analyzer workflows in OpenELIS Global 2:
- Bridge is the runtime owner of directory watching/polling and file transport.
- OpenELIS owns configuration, bridge registration, direct ingestion endpoint, and result processing.
- No OpenELIS app-side FILE poller is implemented in this branch. If a fallback poller is added later, it must remain disabled by default unless explicitly enabled.
When guidance conflicts, this ownership model takes precedence for remediation work in feature 014.
Purpose: This file provides comprehensive project context for ALL AI coding agents (Claude, Cursor, Copilot, Jules, Aider, etc.). It contains everything an AI agent needs to know to work effectively on OpenELIS Global 2.
For Humans: See README.md for project overview and CONTRIBUTING.md for contribution guidelines.
Project Identity
What is OpenELIS Global 2?
OpenELIS Global is an open-source Laboratory Information Management System (LIMS) designed for public health laboratories in resource-limited settings. It manages the complete laboratory workflow from sample collection to result reporting, serving 30+ countries worldwide.
Key Characteristics:
- Healthcare Mission-Critical: Used for HIV/AIDS testing, TB diagnostics, malaria surveillance, COVID-19 testing
- Regulatory Compliance: Meets SLIPTA (Stepwise Laboratory Quality Improvement Process Towards Accreditation) and ISO 15189 standards
- Multilingual: Supports en, fr, ar, es, hi, pt, sw (English, French, Arabic, Spanish, Hindi, Portuguese, Swahili)
- Interoperability: FHIR R4 + IHE standards for integration with national health information exchanges
- Specification-Driven Development: Uses GitHub SpecKit for rigorous feature development workflow
Governance:
- Constitution Authority:
.specify/memory/constitution.md(v1.8.1) is the authoritative governance document - All code changes MUST comply with constitutional principles
- Constitution supersedes all other documentation in case of conflict
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 · 2,335 lines · 19,053 tokens per session scan A 6376eab7a45c
OpenELIS-Global-2 AGENTS.md is an instructions file published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed yesterday), licensed MPL-2.0. It adds 19,053 tokens to every session, about $0.0953 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
HealthClawGuardrails GEMINI.md
Gemini CLI instructions for aks129/HealthClawGuardrails, covering healthclaw guardrails — gemini extension context, what the tools do and how to behave.
hccinfhir CLAUDE.md
Instructions for mimilabs/hccinfhir, covering claude.md, project information, what this library does, development commands and testing.
healthcareskills AGENTS.md
AGENTS.md instructions for aks-builds/healthcareskills, covering agents.md, repository overview, repository structure, agent skills specification and required frontmatter.
healthpoint-rs AGENTS.md
AGENTS.md instructions for edithatogo/healthpoint-rs, covering repository guidelines, project structure, build, test, and development commands, coding style and testing guidelines.
tula CLAUDE.md
Instructions for realactivity/tula, covering claude.md - claude code notes, claude code and quick links.
pyomop AGENTS.md
AGENTS.md instructions for dermatologist/pyomop, covering pyomop: omop swiss army knife, working effectively, build and test commands, code quality tools and cli usage and testing.