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 YuanyuanMa03/academic-research-skills --skill pm-navigate-pagesgit clone --depth 1 https://github.com/YuanyuanMa03/academic-research-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/yuanyuanma03/academic-research-skills/pm-navigate-pages)<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/pm-navigate-pages"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/pm-navigate-pages/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/yuanyuanma03/academic-research-skills/pm-navigate-pages"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/pm-navigate-pages.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 | $0.00028 | $0.00936 |
| Opus 5.5 | $0.00011 | $0.00374 |
| Sonnet 5.5 | $0.00006 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
pm-navigate-pages 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 today.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PubMed Navigate Pages & Sort
Navigate search result pages or change sort order. Requires a previous pm-search call to know the current query, page, and size.
Arguments
$ARGUMENTS can be:
next— go to next pageprevious— go to previous pagepage N— go to page Nsort by date— sort by most recentsort by relevance— sort by best match (default)
Prerequisites
This skill requires context from a previous pm-search call:
query: the search termpage: current page numbersize: results per pagetotal: total results count
Steps
1. Calculate new parameters
Based on $ARGUMENTS:
next: newPage = currentPage + 1previous: newPage = max(1, currentPage - 1)page N: newPage = Nsort by date: sort = "date", newPage = 1sort by relevance: sort = "relevance", newPage = 1
Compute: retstart = (newPage - 1) * size
2. Navigate to updated URL
Use mcp__chrome-devtools__navigate_page:
- url:
https://pubmed.ncbi.nlm.nih.gov/?term={URL_ENCODED_QUERY}&size={size}&page={newPage}
3. Fetch results (evaluate_script)
Same pattern as pm-search step 2, with updated retstart and sort:
async () => {
const query = "PREVIOUS_QUERY";
const page = NEW_PAGE;
const size = CURRENT_SIZE;
const sort = "SORT_VALUE";
const retstart = (page - 1) * size;
const searchResp = await fetch(
`https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=${encodeURIComponent(query)}&retmax=${size}&retstart=${retstart}&retmode=json&sort=${sort}`
);
const searchData = await searchResp.json();
const ids = searchData.esearchresult?.idlist || [];
const total = parseInt(searchData.esearchresult?.count || '0');
if (ids.length === 0) return { query, total, page, results: [] };
const sumResp = await fetch(
`https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id=${ids.join(',')}&retmode=json`
);
const sumData = await sumResp.json();
const results = ids.map((id, i) => {
const r = sumData.result?.[id] || {};
const doi = (r.articleids || []).find(a => a.idtype === 'doi')?.value || '';
return {
n: retstart + i + 1,
pmid: id,
title: r.title || '',
authors: (r.authors || []).map(a => a.name).join(', '),
journal: r.fulljournalname || '',
source: r.source || '',
pubdate: r.pubdate || '',
doi,
pubtype: (r.pubtype || []).join(', ')
};
});
const totalPages = Math.ceil(total / size);
return { query, total, page, totalPages, size, sort, results };
}
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.
- today First seen · 112 lines · 28 tokens per session scan A 2d94a16d6084
pm-navigate-pages is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (75 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 936 once invoked, about $0.0001 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 2026-10-29.
Other skills, from other repositories
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
secops-detection-engineering
Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps. Use when writing new detection rules, tuning existing rules, validating syntax, testing logic against historical telemetry, or evaluating detection coverage against threat intelligence blogs…
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).