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 Aperivue/medsci-skills --skill setup-medscigit clone --depth 1 https://github.com/Aperivue/medsci-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/skills/aperivue/medsci-skills/setup-medsci)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/setup-medsci"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/setup-medsci/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/aperivue/medsci-skills/setup-medsci"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/setup-medsci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 96 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.
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 | $0.00059 | $0.01004 |
| Opus 5.5 | $0.00024 | $0.00402 |
| Sonnet 5.5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
setup-medsci 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 25d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup-MedSci Skill
Diagnose only. Never install, upgrade or configure anything — no brew install,
winget install, pip install, Rscript -e 'install.packages(...)', and no edits to
~/.claude.json or any MCP configuration (read claude mcp list only) — because auto-installers
for system Python and R are a support nightmare for non-developer users. If a tool is missing,
the user follows the setup doc themselves. Skill versions and content are out of scope
(validate_skills.sh, /manage-project status).
The diagnostic table is in English so it can be pasted into a GitHub issue. Remediation links
point to the docs/setup/ guides in the medsci-skills repository, and only these five exist:
docs/setup/README.md, docs/setup/mac.md, docs/setup/windows.md, docs/setup/mcp-setup.md,
docs/setup/common-issues.md.
Workflow
Phase 1: Detect OS
uname -s
Darwin→ macOS →docs/setup/mac.mdLinux→ Linux (similar tooling to Mac) →docs/setup/mac.mdMINGW*,MSYS*,CYGWIN*, or detection failure on Windows →docs/setup/windows.md
Phase 2: Run Diagnostic Commands
Read references/setup-checklist.md and run every check in it — R1-R5 required, O1-O5 optional —
with its detect command, version command, minimum version and status rule. Use command -v <tool>
first to detect presence without running it (avoids triggering long initialization). Capture the
version output and the exit code, and report the version exactly as printed: if a command fails,
report the failure verbatim rather than a version that is "probably" installed. If command -v
finds the tool but the version command or its parse fails, mark the row ❌ and report the failing
command — the install is broken, not just outdated. An MCP server is ✅ only when
claude mcp list shows it connected; configured-but-disconnected is ⚠️.
Phase 3: Emit Checklist Table
Print a single Markdown table to stdout in this exact format, one row per check, with the doc link from the reference for the detected OS:
What ships with it
2 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.
- 25d ago Changed · -25 lines · -3 tokens per session 4f30f5b7db56
- 1mo ago First seen · 111 lines · 62 tokens per session scan A d346a9b883f6
setup-medsci is a skill published in the GitHub repository Aperivue/medsci-skills (349 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,004 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.
clinical-research
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…
sr-search-record
An automated literature-review search and screening workflow using OpenAlex, an open database and API for scholarly research, and Zotero, a reference manager.
review-draft
A workflow for expanding a first draft of a review article into a structured academic manuscript. A review article combines and organizes existing research rather than reporting a new experiment.
review-synthesis
A literature-review workflow that combines evidence from the full text of selected research papers into a findings document. It uses different review methods for systematic, semi-systematic, and integrative reviews.