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 heidihelena/citevahti --skill citevahti-devgit clone --depth 1 https://github.com/heidihelena/citevahtiWrote 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/heidihelena/citevahti/citevahti-dev)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-dev"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-dev/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/heidihelena/citevahti/citevahti-dev"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-dev.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 | $0.00066 | $0.01719 |
| Opus 5 | $0.00033 | $0.00860 |
| Sonnet 5 | $0.00013 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
citevahti-dev 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 10d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti — Citation Integrity for Manuscripts
Overview
CiteVahti runs unit tests on manuscript claims: each claim is a test case, each candidate paper is an assertion. It records a human → AI → adjudication decision chain with a hash-chained audit log.
The human is always the decider. The AI is a blinded advisory second rater only. Nothing is written to Zotero without explicit preview → confirm → commit.
Three doors — same product
| Who says this | What they mean |
|---|---|
| "Run unit tests on my manuscript" | agents / technical users |
| "Check every claim before I cite it" | researchers |
| "Create an auditable claim-evidence trail" | journals / institutions |
Triggers
Use when:
- "Check if this citation supports the claim"
- "Check my references" / "citation integrity"
- "Add to Zotero" after evidence review
- "PRISMA" / "systematic review" / "evidence synthesis"
- "Citation-integrity report" for manuscript methods
[oo]/[o]/[r]/[d]claim states mentioned- "Blinded rating" / "dual rater" for citations
- Desk rejection for citation quality
Do NOT use for: general PubMed search without a manuscript claim, Zotero library management unrelated to claim checking, screening / inclusion decisions.
Setup paths
Path A — FullVahti / Claude Desktop (no terminal)
Download citevahti.mcpb from the latest release, double-click, pick project
folder. Bundled runtime — no Python needed. Run run_claim_tests in chat.
Recommended for non-technical researchers.
Path B — Claude Code (MCP stdio)
pip install "citevahti[keyring,mcp]"
citevahti init
citevahti onboard --ncbi-email [email protected] --no-zotero-key --skip-validate
citevahti connect-zotero
claude mcp add citevahti -- citevahti start --root /path/to/project
Then run run_claim_tests prompt in chat.
citevahti start blocks in terminal — that is correct. It serves MCP stdio
for the chat client. For hands-on terminal use, run citevahti-panel instead.
What ships with it
1 file 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.
- 10d ago First seen · 174 lines · 66 tokens per session scan A 69094ca1f043
citevahti-dev is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,719 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
idea-bib-review
A writing workflow for drafting a literature review from a research idea and BibTeX files, which are structured records of academic sources. It preserves citation keys and checks whether claims are supported by the supplied evidence.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper…
econ-management-paper-polish
A writing and editing guide for papers in economics, management, finance, accounting, marketing, information systems, public administration, and related fields.
socsci-paper-orchestrator
An orchestrator for writing Korean social-science research papers with a team of six specialized agents. Social science studies people, organizations, and society; a research paper presents a question, evidence, methods, and conclusions.