agentmods.dev

citation-faithfulness

citation-faithfulness is a command for Claude Code from CanXiangCC/aminer-open-skill. It costs 0 tokens per session (1,985 once invoked), scanned A, original, MIT.

A command for checking whether claims made with in-text citations are supported by the sources they cite. It retrieves those sources from the web and assigns a verdict to each checked claim.

In plain words
What is it for?
Use it to review the faithfulness of citations in a research-paper PDF, limit the number or scope of references checked, and produce results in a chosen output format.
Why use it?
A citation can exist while still failing to support the sentence that cites it. This check helps distinguish supported, partly supported, unsupported, absent-from-source, and unverifiable claims.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 60repo +1 4d ago A scan 0 tokens original MIT

Good fit Use it to review the faithfulness of citations in a research-paper PDF, limit the number or scope of references checked, and produce results in a chosen output format.

Compare 6 commands from other repositories ↓
View source ↗ CanXiangCC/aminer-open-skill
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add CanXiangCC/aminer-open-skill
Claude Code
/plugin install citation-faithfulness

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/commands/canxiangcc/aminer-open-skill/citation-faithfulness/github.svg)](https://agentmods.dev/commands/canxiangcc/aminer-open-skill/citation-faithfulness)
Your own site
<a href="https://agentmods.dev/commands/canxiangcc/aminer-open-skill/citation-faithfulness"><img src="https://agentmods.dev/badge/commands/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/commands/canxiangcc/aminer-open-skill/citation-faithfulness"><img src="https://agentmods.dev/badge/commands/canxiangcc/aminer-open-skill/citation-faithfulness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,985 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 $0.00000 $0.01985
Opus 5 $0.00000 $0.00992
Sonnet 5 $0.00000 $0.00397
Haiku 4.5 $0.00000 $0.00198

Measured 12d ago against content hash 9cb2b3611b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 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.

skills/citation-faithfulness/commands/citation-faithfulness.md · 105 lines

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.

/citation-faithfulness — Citation Faithfulness Checker

User invoked the Citation Faithfulness skill with:

$ARGUMENTS

Language Routing / 语言路由

  • If $ARGUMENTS or the conversation is mainly Chinese, follow 中文命令流程 and read ${CLAUDE_PLUGIN_ROOT}/SKILL.zh.md + ${CLAUDE_PLUGIN_ROOT}/references/rubric.md + ${CLAUDE_PLUGIN_ROOT}/references/output-schema.md.
  • Otherwise follow English Command Flow and read ${CLAUDE_PLUGIN_ROOT}/SKILL.md + ${CLAUDE_PLUGIN_ROOT}/references/rubric.md + ${CLAUDE_PLUGIN_ROOT}/references/output-schema.md.
  • Parameter names stay English: pdf, scope, max-refs, output.
  • Verdict labels (SUPPORTED / PARTIALLY_SUPPORTED / NOT_SUPPORTED / NOT_IN_SOURCE / UNVERIFIABLE), retrieval_level, and JSON keys stay English.

English Command Flow

1. Pre-flight

Any failed check stops the flow.

  1. Confirm the user gave an existing local .pdf path. If not, ask for one. Never invent or download a paper to check.
  2. Confirm Read, WebSearch, and WebFetch are usable. If there is no web access, warn the user that without retrieving sources every verdict will be UNVERIFIABLE, and ask whether to proceed.
  3. This is the wrong skill if the user wants to know whether a reference exists / is hallucinated — route them to /pdf-citation-verifier instead.
  4. AMINER_API_KEY is optional (enrichment only); do not require it and never echo its value.

2. Parse $ARGUMENTS

Field Values Default Meaning
pdf absolute PDF path required Paper to check
scope all / specific-only / refs:1,12,23 all Which citations to check
max-refs integer none Cap unique sources retrieved (cost guard)
output path ./citation-faithfulness-<pdf-stem>.json Full JSON report path. Always written; defaults to the current working directory, named after the PDF

If pdf is missing or the path does not exist, stop and ask. If scope: all on a reference-heavy paper, warn about cost (~1 web retrieval per unique source) and offer specific-only or max-refs before starting.

Read the full file on GitHub · 105 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. 12d ago First seen · 105 lines · 0 tokens per session scan A 9cb2b3611b83

Subscribe to this mod's changes

citation-faithfulness is a command published in the GitHub repository CanXiangCC/aminer-open-skill (60 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,985 tokens. 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.

DocumentsPDFResearch
Related

Other commands, from other repositories

open

Open a PDF in the in-app viewer panel.

eigenweltlabs/legalwork · 9 tokens

brief-compliance-check

Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.

flonat/flonat-research · 45 tokens

pipeline-minutar-pdf

Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).

georgemarmelstein/superjurista-dev · 27 tokens

docs

Document delivery with export to PPTX, DOCX, PDF formats.

nyldn/claude-octopus · 13 tokens

cti-report

Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].

7onez/cti-expert · 45 tokens

cheatsheet

Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.

OPTIMETA/PAIDEIA · 29 tokens