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.
curl -O https://raw.githubusercontent.com/aks129/HealthClawGuardrails/main/GEMINI.mdgit clone --depth 1 https://github.com/aks129/HealthClawGuardrailsWrote 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/aks129/healthclawguardrails/gemini-md)<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.
<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>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 | $0.00379 | $0.00379 |
| Opus 5 | $0.00189 | $0.00189 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
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.
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-demoholds synthetic data only. For real records, the user supplies their ownX-Tenant-Idand a tenant-bound step-up token.
Project: https://healthclaw.io · Source: https://github.com/aks129/HealthClawGuardrails
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.
- 12d ago First seen · 29 lines · 379 tokens per session scan A 2478178d5ebf
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.
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.
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.
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.
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).
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.
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).