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.
git clone --depth 1 https://github.com/faberlens/hardened-skillsWrote 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/plugins/faberlens/hardened-skills/health-hardened-skills)<a href="https://agentmods.dev/plugins/faberlens/hardened-skills/health-hardened-skills"><img src="https://agentmods.dev/badge/plugins/faberlens/hardened-skills/health-hardened-skills/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/plugins/faberlens/hardened-skills/health-hardened-skills"><img src="https://agentmods.dev/badge/plugins/faberlens/hardened-skills/health-hardened-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
health-hardened-skills 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 9d 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
{
"name": "health-hardened-skills",
"description": "Medical coding, EHR/FHIR, fitness wearables, health records, and wellness.",
"source": "./",
"strict": false,
"skills": [
"./skills/autoicd-hardened",
"./skills/drugbank-hardened",
"./skills/fhir-developer-hardened",
"./skills/garmin-connect-hardened",
"./skills/health-records-hardened",
"./skills/healthcare-mcp-hardened",
"./skills/healthkit-sync-hardened",
"./skills/intimate-wellbeing-hardened",
"./skills/medical-terms-hardened",
"./skills/therapy-mode-hardened"
]
}What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 673 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill healthkit-sync-hardened A 72 tokens
- Skill garmin-pulse-hardened A 46 tokens
- Skill garmin-pulse A 43 tokens
- Skill healthcare-mcp-hardened A 29 tokens
- Skill medical-terms-hardened A 36 tokens
- Skill intimate-wellbeing-hardened A 51 tokens
- Skill clinical-decision-support-hardened A 100 tokens
- Skill clinical-reports-hardened A 74 tokens
- Skill drugbank-database-hardened A 87 tokens
- Skill fhir-developer-skill-hardened A 135 tokens
What ships with it
1 file beside marketplace.json#health-hardened-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 18 lines scan A f22e0ab253e8
health-hardened-skills is a plugin published in the GitHub repository faberlens/hardened-skills (23 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
hf-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
rf-and-mixed-signal
MATLAB, Simulink, Antenna Toolbox, Mixed-Signal Blockset, RF Blockset, RF PCB Toolbox, RF Toolbox, SerDes Toolbox, Signal Integrity Toolbox, Signal Processing Toolbox, and Statistics and Machine Learning Toolbox.
powerskills-tool
Progressive-disclosure workflows for power-system software exposed by PowerMCP: ANDES, Egret, LTSpice, OpenDSS, PSLF, PSS/E, PowerWorld, PyPSA, pandapower, and surge, plus potpourri for AC/DC and multi-period optimal power flow on pandapower distribution grids. Each skill exposes load, inspect, solve, modify, then…
photonforge
PhotonForge PCell, layout, routing, circuit/time-domain simulation, project versioning + cloud-GUI (photonforge-server), serialization, GUI automation, LiveViewer, variation-aware yield/DFM, and documentation guidance for AI coding agents.
cog-happiness-score
Cognitum cog: Happiness Score. Estimates well-being from movement and mood signals.
ltspice-mcp
LTspice/ngspice circuit simulation with structured results — including per-device operating points (gm/gds/vth) read back by name, no rawfile parsing — plus LTspice .asc schematic editing, exposed as MCP tools. Tracks the latest ltspice-mcp release on PyPI.