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 write-protocolgit 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/write-protocol)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/write-protocol"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/write-protocol/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/write-protocol"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/write-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Memory Poisoning · line 92 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Rogue Agent · line 8 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 | $0.00050 | $0.01436 |
| Opus 5.5 | $0.00020 | $0.00574 |
| Sonnet 5.5 | $0.00010 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
write-protocol 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 24d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write-Protocol Skill
Draft the scientific core of an IRB/ethics protocol and leave institution-specific sections as
[TODO] skeletons. Read both reference files before generating a protocol draft:
${CLAUDE_SKILL_DIR}/references/protocol_template.md-- the 10-section structure, per-section guidance, and the[TODO]blocks for Sections 5-9${CLAUDE_SKILL_DIR}/references/ethics_checklist.md-- jurisdiction-specific ethical requirements
Inputs
Collect the required inputs before generating; ask for any that are missing.
- Required: research question / hypothesis (specific, testable); study type (retrospective cohort, prospective cohort, cross-sectional, RCT, diagnostic accuracy, case-control, case series); target population (who, where, when); primary outcome; secondary outcomes (if any).
- Optional: key references (DOIs or search terms); institution name (header and ethics guidance); regulatory context -- Korea (PIPA), US (HIPAA/Common Rule), EU (GDPR), other.
Use prior skill outputs directly when they exist; when they do not, ask the user or call the skill:
- design-study: design recommendations, analysis unit, comparator design, validation strategy.
- calc-sample-size:
protocol/sample_size_justification.md(canonical IRB-ready prose) andprotocol/sample_size_calc.{R,py}(reproducible code). - search-lit: Background references with verified citations.
- define-variables:
variable_operationalization.md-- literature-grounded definitions, cutoffs, DB-variable mappings for the Methods section. Precondition: if the study is observational and no operationalization artifact exists, call/define-variablesbefore drafting Methods. Do not invent phenotype/cutoff definitions from the data dictionary inside this skill.
Protocol Structure -- 10 Sections
Core Sections (Fully Generated)
Section 1: Background and Rationale (400-600 words)
Full paragraphs, no bullet points, flowing from clinical context (disease burden, current
practice) through the knowledge gap and rationale (what this study adds) to the research question
or hypothesis. Call /search-lit if key references are not provided. Cite a reference only with a
/search-lit-confirmed DOI or PMID; otherwise mark it [UNVERIFIED - NEEDS MANUAL CHECK].
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.
- 24d ago Changed · -126 lines · -15 tokens per session 46bd1e3a5913
- 1mo ago Changed · -2 lines 8548d8bbebe1
- 1mo ago First seen · 252 lines · 65 tokens per session scan A 3d2041be27da
write-protocol is a skill published in the GitHub repository Aperivue/medsci-skills (349 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,436 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 2026-09-03.
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.
critical-paper-reading
A paper-reading workflow for critically examining one research paper from a PDF or Zotero item. Zotero is a tool for organising research papers and references.
knowledge-module-gen
A workflow for generating knowledge-module files from a list of academic reading modules. It reads full papers from Zotero, NotebookLM, or local PDFs and records page references and execution checks.