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 yqi96/warranted --skill cite-reviewgit clone --depth 1 https://github.com/yqi96/warrantedWrote 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/yqi96/warranted/cite-review)<a href="https://agentmods.dev/skills/yqi96/warranted/cite-review"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/cite-review/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/yqi96/warranted/cite-review"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/cite-review.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 | $0.00052 | $0.01601 |
| Opus 5 | $0.00026 | $0.00800 |
| Sonnet 5 | $0.00010 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
cite-review 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Every \cite{statement_N} in the tex must faithfully represent the content of Statement N. A citation that overstates, understates, or mischaracterises what the Statement says is a citation error.
Done means: every citation has been reviewed; every mismatch has been resolved by either (a) creating a corrected Statement and updating the citation, or (b) rewriting or removing the offending LaTeX. Consequences this skill cannot close on its own — a Claim reverted to proposed, a stale compile — are named as open gaps, not silently left.
Phase 1 — Extract In Resident Context
Identify the .tex file(s). If the user did not specify a path, find .tex files in the project directory.
Scan the tex for every \cite{...} containing statement_N keys. A single \cite{} may carry multiple keys, e.g. \cite{statement_1, statement_3}. For each key in each cite, emit one tuple (statement_id, file_path, line_number) — a flat list, one entry per statement per cite occurrence. Do not read surrounding text, call get_node, or open any PDF here. Hand the list to Phase 2.
Phase 2 — Parallel per-cite review
Delegate one bounded review per (statement_id, file_path, line_number) tuple, all in parallel. Each review is self-contained and answers a single question: does the citing sentence faithfully represent Statement N?
The check:
- Extract the sentence(s) carrying the factual claim this cite supports as
latex_claim— enough that the assertion is unambiguous. If the\cite{}lists multiple keys, this review still judges onlystatement_id; siblings share the samelatex_claim. - Compare
latex_claimagainst Statement N'scontent. Faithful means the LaTeX makes no stronger, weaker, or categorically different claim than the Statement; paraphrase is fine, mischaracterisation is not. - If faithful →
MATCH. - On mismatch, read the Statement's attached paper and determine whether
latex_claimis directly extractable — in text, a table, or a figure — without inference or aggregation.
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.
- 9d ago First seen · 111 lines · 52 tokens per session scan A fcc698df0cba
cite-review is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 1,601 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
proof-checker
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
auto-paper-improvement-loop
An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.
paper-write
A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.
research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
experiment-bridge
A workflow that turns an experiment plan into code, reviews the code, runs an initial check, deploys experiments, and collects early results. Deployment means sending the experiment to the environment where it will run, such as a GPU machine.