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-reportgit 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-report)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-report"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-report/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-report"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-report.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 | $0.00078 | $0.01319 |
| Opus 5 | $0.00039 | $0.00660 |
| Sonnet 5 | $0.00016 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
citevahti-report 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti report — package the audit for a human reader
citevahti-dev produces the machine record: the ledger of claims, states, and the
hash-chained audit trail. This skill turns that record into what a person reads —
a methods paragraph, an evidence appendix, and an inspectable audit trail a supervisor
or journal can check. It writes about the audit; it never re-runs it.
Triggers
Use when the researcher asks to:
- write the methods text describing how citations were checked
- export or share the audit trail / integrity summary
- assemble an evidence appendix for submission or a supervisor
- get a pre-submission summary of claim states before they submit
Do NOT use when: claims are still unrated (run citevahti-dev first), or the ask is
to check a new claim, screen a bibliography (citevahti-screen), review someone else's
manuscript (citevahti-review), or draft body text (citevahti-writing).
Prerequisite
The ledger exists and its claims are decided. Confirm with citevahti status; if claims
are still [u] untestable or [r] review-needed, stop and hand back to citevahti-dev —
a report over an unfinished audit misrepresents the work.
What it produces (each from a real command; no number is invented)
- Methods paragraph —
citevahti methods. Plain prose describing the workflow actually used, plus the PRISMA-style discovery/flow disclosure: claims checked against cited sources through a blinded human rating with an advisory AI second opinion, disagreements adjudicated by the human, references written to Zotero as an audited step. States what was done, never that the result is certified. - Integrity summary —
citevahti report --format md. The claim-state table:[oo]accepted,[o]needs-support,[r]review-needed,[d]decided (rejected),[u]untestable, with counts. - Evidence appendix —
citevahti evidence-export --format markdown. Per claim: the sentence, the source cited, the support rating, and the human decision. The reviewer-facing companion to the ledger. (--format csv/csl-jsonalso available.) - Audit-trail check —
citevahti verify-audit. Recomputes the hash chain over.citevahti/audit_log.jsonland reports whether it is intact (tamper-evident), so a supervisor or journal can confirm the record has not been altered. - (Optional) Agreement numbers —
citevahti agreement-report --metric cohen_kappafor human↔AI agreement, when a methods section reports it.
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 · 102 lines · 78 tokens per session scan A 8534bf24fdb5
citevahti-report is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,319 once invoked, about $0.0004 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.