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-writinggit 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-writing)<a href="https://agentmods.dev/skills/heidihelena/citevahti/citevahti-writing"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-writing/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-writing"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/citevahti-writing.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 | $0.00065 | $0.00950 |
| Opus 5 | $0.00032 | $0.00475 |
| Sonnet 5 | $0.00013 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
citevahti-writing 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteVahti Writing — AI-Assisted Drafting from Checked Evidence
Overview
Coordinates the MatchVahti → CiteVahti → AI writing chain. The researcher reviews evidence first, marks citation slots, CiteVahti checks and commits to Zotero, then AI drafts prose — drawing only on claims the human has already adjudicated.
The AI writes from checked evidence. It never invents citations.
The chain
MatchVahti-Lite (browser) MatchVahti (app)
tap citable sentence blinded claim×paper loop
[oo] closer-look flag MatchResult in .citevahti/
export .ris → Zotero full-text claim checking
↓ ↓
└─────────────┬─────────────────┘
↓
CiteVahti (.citevahti/ ledger)
claim checked → [oo] accepted → Zotero
↓
AI drafts prose from checked claims only
human reviews → accepts / edits / rejects
↓
Manuscript with auditable citation trail
Triggers
Use when:
- "Write a paragraph about X, I've checked the references"
- "Draft the discussion based on what I found in MatchVahti"
- "I marked [needs citation] — find and check, then draft"
- "Expand this sentence with the evidence I cited"
[oo]/cite:closer-looktags in Zotero mentioned- Manuscript has
[REF]/<!-- cite: -->/(XXX et al.)slots
Do NOT use: before researcher has reviewed evidence, to invent citations, to bypass the human decision step.
Workflow
Before drafting — establish evidence state:
| Researcher comes from | What to check | Ready when |
|---|---|---|
| MatchVahti-Lite | Zotero has cite:abstract-only items |
Human has reviewed .ris import |
| MatchVahti (app) | .citevahti/ ledger has MatchResult |
Claim is [oo] or [o] |
| Neither | — | Run citevahti-dev first, return here |
Never draft from [r] review, [d] rejected, or unchecked claims.
Map citation slots → check ledger → draft → human review → insert citekeys.
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.
- 12d ago First seen · 105 lines · 65 tokens per session scan A 4c49b0dd789a
citevahti-writing is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 65 tokens to every session and 950 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.