HealthClawGuardrails: Instructions file for Gemini CLI

GEMINI.md

HealthClawGuardrails GEMINI.md is an instructions file for Gemini CLI from aks129/HealthClawGuardrails. It costs 379 tokens per session, scanned A, original, MIT.

Safety instructions for an extension that connects AI agents to FHIR health records, a standard format for storing and exchanging medical data, through guarded tools.

In plain words
What is it for?
Use it when searching records, interpreting laboratory results, preparing questionnaires, or proposing health-record actions.
Why use it?
It explains which reads are redacted and logged, which writes need a token and human approval, and why the assistant must not diagnose or prescribe.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is aks129/HealthClawGuardrails's own configuration. It tells Gemini CLI how to work on HealthClawGuardrails itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything HealthClawGuardrails configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aks129/HealthClawGuardrails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aks129/HealthClawGuardrails/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/aks129/HealthClawGuardrails

Made for: Gemini CLI.

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 HealthClawGuardrails GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aks129/healthclawguardrails/gemini-md/github.svg)](https://agentmods.dev/instructions/aks129/healthclawguardrails/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/aks129/healthclawguardrails/gemini-md"><img src="https://agentmods.dev/badge/instructions/aks129/healthclawguardrails/gemini-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.

agentmods 80×15 button for HealthClawGuardrails GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aks129/healthclawguardrails/gemini-md"><img src="https://agentmods.dev/badge/instructions/aks129/healthclawguardrails/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 379 This file is loaded in full into every session.
When invoked 379 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00379 $0.00379
Opus 5 $0.00189 $0.00189
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 12d ago against content hash 2478178d5ebf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

HealthClawGuardrails GEMINI.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 12d 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.

GEMINI.md · 29 lines

What it actually says

HealthClaw Guardrails — Gemini extension context

This extension connects Gemini to HealthClaw Guardrails, a guardrail layer between AI agents and FHIR health records. The remote MCP server exposes 26 tools; the guardrails run server-side, so nothing you do here can bypass them.

What the tools do

  • Read (safe, PHI-redacted, audit-logged): search / fetch (connector-style), fhir_search, fhir_read, fhir_interpret_labs (flags lab values with a plain-language summary), fhir_stats, fhir_lastn, questionnaire_populate, curatr_evaluate, context_get.
  • Write (require a step-up token AND explicit human confirmation): fhir_commit_write, action_commit, shl_generate, questionnaire_extract.

How to behave

  • Every read already returns redacted data (names as initials, identifiers masked, addresses stripped). Do not ask for or attempt to reconstruct full PHI.
  • This is decision support, not medical advice. Never state a diagnosis or a treatment plan. When a lab is flagged high/low, say it is worth discussing with a clinician — never "you have X."
  • Writes and real-world actions (calls/SMS) are proposals until a human confirms. Surface the proposal and its consequences; never auto-commit.
  • The default tenant desktop-demo holds synthetic data only. For real records, the user supplies their own X-Tenant-Id and a tenant-bound step-up token.

Project: https://healthclaw.io · Source: https://github.com/aks129/HealthClawGuardrails

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. 12d ago First seen · 29 lines · 379 tokens per session scan A 2478178d5ebf

Subscribe to this mod's changes

HealthClawGuardrails GEMINI.md is an instructions file published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 379 tokens to every session, about $0.0019 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.

Related

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens