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-reviewgit 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-review)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-review"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-review/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-review"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-review.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 | $0.00070 | $0.01064 |
| Opus 5 | $0.00035 | $0.00532 |
| Sonnet 5 | $0.00014 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
citevahti-review 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti review — the reviewer's and editor's pass
citevahti-dev is for auditing your own manuscript, with write-back to your Zotero.
This skill is for auditing someone else's — as a peer reviewer or editor. It checks
whether each cited source supports the claim, and produces a structured report you fold
into your review. It changes nothing in the author's files.
Triggers
Use when the reviewer or editor asks to:
- check whether the citations in a manuscript under review actually support its claims
- produce a reviewer report of unsupported or overstated claims
- assess a submission's evidence before recommending a decision
Do NOT use when: the manuscript is the user's own (citevahti-dev), or the ask is to
screen a plain reference list for retractions (citevahti-screen).
What makes it different from citevahti-dev
- Read-only, and library-free. You review from the submission text, not the author's
Zotero. The core command is
citevahti claim-verify --claim "<claim>" --text-file <source-excerpt>— it checks a claim against provided text, offline, with no Zotero and no network. It writes nothing. - Assess, don't author. You are judging whether the source supports the claim, not fixing the wording. Suggested wording goes to the author as a comment, never as an edit.
There is no single citevahti review <file> command — the review is a read-only pass of
claim-verify (and claim-check, if you happen to have the sources in a library) over the
submission's cited claims, assembled into a report.
Workflow
# per cited claim, against the passage the author quotes/cites:
citevahti claim-verify --claim "<the manuscript claim>" --text-file <source-passage>.txt
For each cited claim, assess support (blinded human first, advisory AI second) and draft a report entry: the claim, the source cited, the support assessment, and a neutral query you can raise with the author.
Output — a reviewer report
Ranked by how far the source falls short of the claim. Each entry:
- the manuscript claim and the source cited for it
- the support assessment, using CiteVahti's frozen vocabulary — supports / contrasts / unclear / not_relevant (never an invented scale)
- a suggested, neutral reviewer comment ("The cited source studied population X; the claim generalizes to Y — please reconcile or qualify.")
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.
- 12d ago First seen · 91 lines · 70 tokens per session scan A f9dfb2ad36cd
citevahti-review is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,064 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.