citevahti: Skill for Claude Code

.claude/skills/prescreen-benchmark/SKILL.md

prescreen-benchmark is a skill for Claude Code from heidihelena/citevahti. It costs 240 tokens per session (2,120 once invoked), scanned A, original, Apache-2.0.

A benchmark for testing local language models as agents that check whether claims are supported by their cited sources. It compares their ratings with independently prepared labels and produces a report.

In plain words
What is it for?
Use it to evaluate models such as Ollama-based models on citation checking for a chosen topic, then review the agreement results in a publication-style report.
Why use it?
It helps reveal whether smaller models judge citation evidence reliably instead of assuming that a model's confident answer is correct.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is heidihelena/citevahti's own configuration. It tells Claude Code how to work on citevahti itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything citevahti configures →

Part of the citevahti plugin — 13 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to heidihelena/citevahti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/heidihelena/citevahti/main/.claude/skills/prescreen-benchmark/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/heidihelena/citevahti

Made for: Claude Code.

Or install citevahti, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

Wrote 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.

agentmods badge for prescreen-benchmark

README.md
[![agentmods](https://agentmods.dev/badge/skills/heidihelena/citevahti/prescreen-benchmark/github.svg)](https://agentmods.dev/skills/heidihelena/citevahti/prescreen-benchmark)
Your own site
<a href="https://agentmods.dev/skills/heidihelena/citevahti/prescreen-benchmark"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/prescreen-benchmark/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.

agentmods 80×15 button for prescreen-benchmark

Your own site · 80×15
<a href="https://agentmods.dev/skills/heidihelena/citevahti/prescreen-benchmark"><img src="https://agentmods.dev/badge/skills/heidihelena/citevahti/prescreen-benchmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00240 $0.02120
Opus 5 $0.00120 $0.01060
Sonnet 5 $0.00048 $0.00424
Haiku 4.5 $0.00024 $0.00212

Measured 9d ago against content hash 431612ac2e97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prescreen-benchmark 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 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/bench.py, scripts/ingest.py, scripts/prompt_v2.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/prescreen-benchmark/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prescreen benchmark — local LLMs as CiteVahti prescreening agents

This skill runs the experiment: take a topic, author a small corpus of claim ↔ cited-source pairs each with an independently-authored anchor label, have local Ollama models (plus a Claude column) prescreen every pair blind, then measure agreement, ingest the run into a dedicated CiteVahti store, and render a self-contained prescreen report.

Naming. This report is not the Atlas. In CiteVahti, Atlas means the panel's claim↔evidence graph (nodes and links — panel/web/evidence-map.js, Spine layout). What this skill renders is a scoreboard and a rating matrix, so it is called the prescreen report (scripts/report.py). Pages published before this rename still carry the old "Evidence Atlas" masthead; leave them as they are.

CiteVahti is a local-first citation-integrity tool used in live pilots with real researchers. A benchmark that overstates what a laptop model can do — or that quietly grades a model against its own author — is exactly the kind of self-flattering evidence this product exists to prevent. So the guardrails below are load-bearing, not decoration.

Non-negotiable guardrails (read first)

  1. The anchor must be authored independently of every rater. Agreement is not accuracy (house doctrine). If the same author writes the claims and the anchor and rates them, a 100% score is self-consistency, not correctness. Best: the clinician/domain expert (or a cited guideline document) supplies the anchor labels; the models — Claude included — are then scored against that anchor through the identical blind prompt. Whenever the anchor was NOT independently authored, say so in the write-up.
  2. Frozen vocabulary. Exactly four coarse labels: supports, contrasts, unclear, not_relevant. Never invent a new scale. (ingest.py maps these onto CiteVahti's canonical 7-value support vocabulary.)
  3. Never touch the real pilot ledger. Every run ingests into a separate root (~/Documents/CiteVahti-<theme>). The founder's ledger at ~/Documents/CiteVahti is off-limits.
  4. Blind + human-first. Models never see the anchor. In the store the anchor is the human rating; the model is the blind AI second opinion; divergences are adjudicated to the anchor.
  5. Trust language. In any report copy: check / assess, never verify / prove / guarantee. The report already carries the "agreement ≠ accuracy" caveat — keep it.

Read the full file on GitHub · 133 lines

Changes

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.

  1. 9d ago First seen · 133 lines · 240 tokens per session scan A 431612ac2e97

Subscribe to this mod's changes

prescreen-benchmark is a skill published in the GitHub repository heidihelena/citevahti (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 240 tokens to every session and 2,120 once invoked, about $0.0012 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.

Related

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.

davila7/claude-code-templates · 65 tokens

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.

bahayonghang/my-ai-cli-toolkit · 126 tokens

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.

OpenLAIR/dr-claw · 65 tokens

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…

Galaxy-Dawn/claude-scholar · 72 tokens

econ-management-paper-polish

A writing and editing guide for papers in economics, management, finance, accounting, marketing, information systems, public administration, and related fields.

linkingoscar/econ-management-paper-polish · 83 tokens

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.

parkjui92/socsci-paper-kit · 384 tokens