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.
npx skills add aks-builds/healthcareskills --skill clinical-decision-supportgit clone --depth 1 https://github.com/aks-builds/healthcareskillsWrote 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/skills/aks-builds/healthcareskills/clinical-decision-support)<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/clinical-decision-support"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/clinical-decision-support/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/skills/aks-builds/healthcareskills/clinical-decision-support"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/clinical-decision-support.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 | $0.00167 | $0.03365 |
| Opus 5 | $0.00084 | $0.01682 |
| Sonnet 5 | $0.00033 | $0.00673 |
| Haiku 4.5 | $0.00017 | $0.00336 |
Grade A, and why
clinical-decision-support 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Decision Support
You are an expert in clinical decision support (CDS) design and implementation. Your goal is to help build CDS that clinicians actually use — meaning it lands in the workflow at the right moment, with the right person, in the right format, and does not contribute to alert fatigue. CDS that is technically correct but ignored is, in practice, broken.
Initial Assessment
Read .agents/healthcare-context.md first (fall back to .claude/healthcare-context.md). The context file tells you the EHR vendor (which dictates CDS Hooks support, BPA tooling, and order-set platforms), the clinical setting (inpatient vs. ambulatory vs. ED), and the regulatory posture (whether the tool is positioned as HHS-exempt CDS, an enterprise tool, or an FDA-cleared SaMD).
If the context file does not exist, ask:
- What is the clinical decision being supported? Who makes it, in what setting?
- What action should the CDS suggest, and what is the workflow consequence?
- Which EHR(s)?
- Is the CDS intended to be HHS-exempt CDS, or are you positioning it as a SaMD?
- Will it be interruptive (modal) or passive (sidebar / FYI)?
The 5 Rights of CDS
Every CDS evaluation should run through these 5 dimensions. If any one is wrong, the CDS will fail — even if the underlying logic is correct.
| Right | Question |
|---|---|
| Right information | Is the recommendation evidence-based, current, specific, and actionable? |
| Right person | Does it go to the clinician who can act on it (not every clinician who touches the chart)? |
| Right format | Modal, side panel, infobutton, banner, order set, dashboard — chosen to match urgency? |
| Right channel | EHR alert, secure message, email, page, mobile push? |
| Right time | At a moment when the clinician can act — not 12 hours after the decision was already made? |
The fifth right (right time) is where most CDS fails — fired too early (before the order is being placed), too late (after the order is signed), or all the time (no contextual filter).
What ships with it
3 files beside SKILL.md 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.
- 12d ago First seen · 287 lines · 167 tokens per session scan A 12a918b528d4
clinical-decision-support is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed 3d ago), licensed MIT. It adds 167 tokens to every session and 3,365 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
european-medical-cv-analyzer
Analyzes physician/medical CVs for residency, specialist-training, or clinical job applications within European (EU/EEA) healthcare systems. Use this skill whenever a user shares a doctor's/physician's CV or resume and asks for feedback, review, scoring, ATS-readiness, or improvement suggestions — even if they don't…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.