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 TurtleTech-ehf/ookcite-mcp --skill verify-referencesgit clone --depth 1 https://github.com/TurtleTech-ehf/ookcite-mcpWrote 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/turtletech-ehf/ookcite-mcp/verify-references)<a href="https://agentmods.dev/skills/turtletech-ehf/ookcite-mcp/verify-references"><img src="https://agentmods.dev/badge/skills/turtletech-ehf/ookcite-mcp/verify-references/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/turtletech-ehf/ookcite-mcp/verify-references"><img src="https://agentmods.dev/badge/skills/turtletech-ehf/ookcite-mcp/verify-references.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 | $0.00047 | $0.00308 |
| Opus 5.5 | $0.00019 | $0.00123 |
| Sonnet 5.5 | $0.00009 | $0.00062 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
verify-references 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 11d 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.
What it actually says
Verify with the OokCite connector before the user relies on a citation. A DOI that fails, and a claim that disagrees with the resolved record, stays out of the manuscript.
- Take DOIs from the references. When a reference has no DOI, call
reverse_lookuporbatch_resolveand use a DOI only if the tool returns one. Do not invent a DOI. - Call
verify_referenceswithdois. When the reference states a title, authors, year, journal, volume, issue, or pages, pass the same positions inclaims. Each claim may settitle,authors(family names),year,journal,volume,issue, andpages. An empty claim only checks that the DOI exists. - Treat
MISMATCHas a failed check, distinct from a DOI that does not exist. Report each item's status in the reply. - Prefer
verify_referencesover onevalidate_doicall per reference. More than 8 metered items on an anonymous session is refused; ask the user to sign in or split the list. - Do not add a failed or mismatched reference to the text the user will submit.
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.
- 11d ago First seen · 13 lines · 47 tokens per session scan A 0f2b87f28b76
verify-references is a skill published in the GitHub repository TurtleTech-ehf/ookcite-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 308 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 2026-10-05.
Other skills, from other repositories
scholar-workflow
Use when the user asks you to search, retrieve, or reason about scholarly sources — papers, patents, books, or standards — guides tool selection, chaining, and cross-domain workflows.
statcite
Fetch official macroeconomic and sovereign statistics (GDP, inflation/CPI, unemployment, government debt, fiscal balance, current account, trade, FDI, population, exchange rates) with full source citations from World Bank WDI, IMF WEO, BIS, ECB and the Eastern Caribbean Central Bank and Central Bank of Barbados via…
scopus-researcher
Expert academic researcher using the Scopus MCP. Finds papers, retrieves full abstracts, builds author profiles, analyzes citation impact, and constructs advanced Boolean queries across the Elsevier Scopus database. Activate when asked to search for academic papers, analyze research trends, find citations, profile…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.