citation-faithfulness

citation-faithfulness is a skill for Claude Code from CanXiangCC/aminer-open-skill. It costs 274 tokens per session (3,442 once invoked), scanned A, original, MIT.

A checker that compares claims in a research paper with the original sources cited for them.

In plain words
What is it for?
It helps review citation accuracy in a PDF by retrieving cited sources and judging whether each claim is faithful.
Why use it?
It helps find distorted conclusions, incorrect numbers, wrong attributions, and claims that sources do not support.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; built for openclaw.

Part of the citation-faithfulness plugin — 1 skill, 1 command shipped together

Good fit It helps review citation accuracy in a PDF by retrieving cited sources and judging whether each claim is faithful.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/canxiangcc/aminer-open-skill/citation-faithfulness
Install

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.

Any agent
npx skills add CanXiangCC/aminer-open-skill --skill citation-faithfulness
Clone the repo
git clone --depth 1 https://github.com/CanXiangCC/aminer-open-skill

Made for: Claude Code.

Or install citation-faithfulness, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 citation-faithfulness

README.md
[![agentmods](https://agentmods.dev/badge/skills/canxiangcc/aminer-open-skill/citation-faithfulness/github.svg)](https://agentmods.dev/skills/canxiangcc/aminer-open-skill/citation-faithfulness)
Your own site
<a href="https://agentmods.dev/skills/canxiangcc/aminer-open-skill/citation-faithfulness"><img src="https://agentmods.dev/badge/skills/canxiangcc/aminer-open-skill/citation-faithfulness/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 citation-faithfulness

Your own site · 80×15
<a href="https://agentmods.dev/skills/canxiangcc/aminer-open-skill/citation-faithfulness"><img src="https://agentmods.dev/badge/skills/canxiangcc/aminer-open-skill/citation-faithfulness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 274 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,442 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00274 $0.03442
Opus 5 $0.00137 $0.01721
Sonnet 5 $0.00055 $0.00688
Haiku 4.5 $0.00027 $0.00344

Measured 9d ago against content hash 7712d3bf5f12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

citation-faithfulness 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.

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.

skills/citation-faithfulness/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Citation Faithfulness Checker

Verify whether the in-text citations in a paper PDF are faithful to the original sources. For each place the paper says "according to [X], …" or "[X] reports …", this skill retrieves what X actually says and judges whether the paper's claim is genuinely supported — catching misrepresentation, reversed conclusions, wrong attribution, mismatched numbers, and claims the source never made.

This is agent-driven: there is no upload service and no bundled script. Claude reads the PDF, retrieves sources with its own web tools, and applies the judging rubric itself. Invoke via natural language or /citation-faithfulness.

What This Skill Does vs. Does Not

This skill (citation-faithfulness) pdf-citation-verifier
Question Does the cited source actually support the claim? Does the reference exist at all?
Catches Distortion, reversed meaning, wrong numbers, over-claiming Ghost references, fabricated DOIs
Method Read PDF + web-retrieve source + agent judges Upload PDF to AMiner service
Key none required needs AMINER_API_KEY

If the user actually wants existence/hallucination checking, stop and route them to pdf-citation-verifier.

Verdict Labels

Each checked claim–source pair gets exactly one verdict (keep the English label in JSON/tables; explain in the user's language):

  • SUPPORTED — the source clearly states what the paper attributes to it.
  • PARTIALLY_SUPPORTED — the source supports part of the claim but the paper overstates, narrows, or adds qualifiers the source did not make.
  • NOT_SUPPORTED — the source addresses the topic but says something different or opposite (a genuine misrepresentation).
  • NOT_IN_SOURCE — the retrieved source (full text) simply does not contain the claimed fact/result.
  • UNVERIFIABLE — the source could not be retrieved, or only an abstract was available and the claim targets a detail the abstract does not cover. This is not an accusation — it means "we could not check", not "the citation is wrong".

Read the full file on GitHub · 173 lines

Files

What ships with it

4 files 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.

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 Changed 7712d3bf5f12
  2. 13d ago First seen · 173 lines · 274 tokens per session scan A fbc98f9b4740

Subscribe to this mod's changes

citation-faithfulness is a skill published in the GitHub repository CanXiangCC/aminer-open-skill (60 stars, last pushed 5d ago), licensed MIT. It adds 274 tokens to every session and 3,442 once invoked, about $0.0014 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 2026-08-30.

Related

Other skills, from other repositories