An integration that runs HealthClaw’s health-data guardrails inside Hermes, an AI agent that can connect to several chat services and retain conversation-based learning. It uses the same HealthClaw server, skills, and safety rules as the OpenClaw integration.

It helps run HealthClaw through Telegram, Discord, Slack, Signal, WhatsApp, or a command line, use native MCP connections, and improve skills from past conversations.

It lets HealthClaw operate through Hermes’ multi-service gateways and native MCP support while keeping the existing guardrails. It also keeps Hermes skills separate from OpenClaw migration imports.

hermes — Skill for Claude Code and Codex by aks129

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/aks129/HealthClawGuardrails

agentmods

npx agentmods add skills/aks129/healthclawguardrails/hermes

Made for: Claude Code, Codex.

Or install healthclaw-guardrails, the plugin that ships this one along with the rest of its 14 skills, 3 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aks129/healthclawguardrails/hermes/github.svg)](https://agentmods.dev/skills/aks129/healthclawguardrails/hermes)

Your own site

<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/hermes"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/hermes/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/hermes"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/hermes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,955 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 85
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
medium Rogue Agent · line 105
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00101	$0.01955
Opus 5	$0.00051	$0.00978
Sonnet 5	$0.00020	$0.00391
Haiku 4.5	$0.00010	$0.00196

Measured 12d ago against content hash 5b2e5cc8162e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hermes scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `/mcp list` shows healthclaw-hosted as disconnected | Outbound HTTPS blocked, or Railway cold start. `curl https://mcp-demo-production-ee2c.up.railway.app/health` — if 200, retry. |

skills/hermes/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes — self-improving HealthClaw gateway

HealthClaw works as a Hermes agent the same way it works as an OpenClaw bot: a SOUL persona on top of the same MCP server with the same guardrails. The difference is Hermes treats every conversation as training data for its skill library, so the integration gets better the more you use it.

When to reach for Hermes instead of OpenClaw

You want…	Use
One Telegram bot with fixed slash commands you trust	OpenClaw
Multi-gateway chat — Telegram + Discord + Slack + Signal + WhatsApp + CLI	Hermes
Skills that learn from your past conversations	Hermes
To run agents on Modal / Daytona / Vercel Sandbox / SSH	Hermes
Native MCP client (no JSON-RPC HTTP bridge)	Hermes
Already invested in `AGENTS.md` + persona workspaces	OpenClaw

They share the same MCP server, the same skills library, the same guardrails — so running both is fine. The HealthClaw install for Hermes lands skills at ~/.hermes/skills/healthclaw/, separate from any OpenClaw migration imports at ~/.hermes/skills/openclaw-imports/.

Setup (~2 minutes)

1. Install Hermes

Follow the upstream instructions at github.com/nousresearch/hermes-agent. At the end you should have a hermes CLI on PATH and a ~/.hermes/ directory.

2. Wire HealthClaw

From the HealthClaw repo root:

./hermes/install.sh

Idempotent — re-run any time. Flags:

--dry-run shows what it would do without touching anything
--skills-only refreshes just the skills (use after you've edited them and want the repo copy back)

The installer:

copies every skill in skills/ to ~/.hermes/skills/healthclaw/
installs the SOUL.md persona at ~/.hermes/personas/healthclaw.md
merges three MCP server entries (hosted, local, SHARP) into ~/.hermes/config.json

3. Use it

hermes
> /persona healthclaw
> /mcp list                       # confirms healthclaw-hosted connected
> show me my conditions
> what's my last HbA1c?
> propose adding a new allergy: peanut, moderate severity

Read the full file on GitHub · 144 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.

12d ago First seen · 144 lines · 101 tokens per session scan A 5b2e5cc8162e

Subscribe to this mod's changes

hermes is a skill published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,955 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents agents ai-agents fhir health-data healthai healthcare

healthcare-fhir

Design RESTful clinical data exchanges using HL7 FHIR standards.

andreibesleaga/GABBE · 17 tokens

lab-report-walkthrough

Walk a person through their lab report — read the original document, organize results by panel, flag out-of-range values against the printed reference ranges, compare with their history, and explain in plain language. Use when the user uploads a lab report (PDF/image) or asks what their blood test results mean.

thetahealth/mirobody · 67 tokens

healthcare-expert

Expert-level healthcare systems, medical informatics, HIPAA compliance, and health data standards. Use when the user mentions medical, HIPAA, HL7, FHIR, or EHR, or when the task involves Healthcare IT, Standards and Protocols, Regulatory Compliance, or Security and Compliance.

personamanagmentlayer/pcl · 64 tokens

hl7gen

Use when generating, validating, or converting HL7 v2 healthcare messages, or converting HL7 v2 to FHIR. Covers synthetic test-message generation for any of 185 HL7 v2 message types across versions 2.1–2.8.2, message validation, FHIR R5/R4B conversion, and structure exploration (required/optional/repeating fields).…

mwaseem75/hl7gen · 131 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

hermes