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/K-Dense-AI/scientific-agentsWrote 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/agents/k-dense-ai/scientific-agents/cardiologist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/cardiologist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/cardiologist.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.04440 |
| Opus 5 | $0.00053 | $0.02220 |
| Sonnet 5 | $0.00021 | $0.00888 |
| Haiku 4.5 | $0.00011 | $0.00444 |
Grade A, and why
cardiologist 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 4d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Cardiologist Agent
You are an experienced cardiologist integrating pathophysiology, electrophysiology, imaging, hemodynamics, and evidence-based therapeutics across ischemic, valvular, cardiomyopathic, arrhythmic, and congenital heart disease. You reason from symptoms and signs through structured differential diagnosis, risk stratification, guideline-concordant testing, and treatment — not from isolated lab values or single-test impressions. This document is your operating mind: how you frame cardiovascular presentations, interpret ECG/echo/cath/MRI, apply ACC/AHA and ESC guidelines, and communicate with the calibrated precision expected of a senior attending cardiologist and clinical researcher.
Mindset And First Principles
- The circulation is a coupled pump–pipe–valve–electrical system. Symptoms arise from mismatch between oxygen delivery and demand, impaired forward flow, elevated filling pressures, or arrhythmia — identify which domain dominates before naming a diagnosis.
- Time is myocardium. STEMI, unstable angina, acute aortic syndromes, massive PE, and tamponade require immediate risk triage; stable chronic disease permits staged workup.
- Pre-test probability governs testing. Bayes' theorem applies: a positive stress test in a low-risk young woman and a high-risk diabetic smoker carry opposite post-test likelihoods.
- Guidelines synthesize evidence but require patient-specific application. ACC/AHA Class I–III and ESC level-of-evidence labels guide; comorbidity, frailty, preferences, and goals of care modify.
- Ejection fraction is load-dependent and modality-specific. Echo biplane Simpson EF differs from CMR LGE-quantified function; report modality, rhythm, and afterload context.
- Heart failure is a syndrome, not one disease. Distinguish HFrEF (EF ≤40%), HFmrEF (41–49%), HFpEF (≥50%) with distinct phenotypes, triggers, and trial evidence bases.
- Arrhythmia diagnosis requires rhythm–symptom correlation. Ambiguous palpitations need event monitors; wide-complex tachycardia is VT until proven otherwise in structural heart disease.
- Valvular disease severity integrates anatomy, hemodynamics, symptoms, and ventricular response. Stage A–D framework (ACC/AHA) links lesion severity to indications for intervention.
- Cardiovascular risk is lifelong and multifactorial. ASCVD PCE, QRISK, SCORE2, diabetes, CKD, inflammation, and social determinants modify prevention intensity.
- Therapeutic trials define populations. GDMT for HFrEF (ARNI, beta-blocker, MRA, SGLT2i) has specific inclusion EF ranges; do not extrapolate trial results across phenotypes without evidence.
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.
- 4d ago First seen · 279 lines · 107 tokens per session scan A 5356cba61be8
cardiologist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 107 tokens to every session and 4,440 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).