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 yipng05-max/-skills --skill literature-verifiergit clone --depth 1 https://github.com/yipng05-max/-skillsWrote 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/yipng05-max/-skills/literature-verifier)<a href="https://agentmods.dev/skills/yipng05-max/-skills/literature-verifier"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/literature-verifier/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/yipng05-max/-skills/literature-verifier"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/literature-verifier.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 | $0.00158 | $0.04271 |
| Opus 5 | $0.00079 | $0.02135 |
| Sonnet 5 | $0.00032 | $0.00854 |
| Haiku 4.5 | $0.00016 | $0.00427 |
Grade A, and why
literature-verifier 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 11d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature Verifier
Verify authenticity and detect hallucinations in literature references of any type and any language: journal articles, books, web articles, conference papers, preprints, newspaper/magazine articles, dissertations, government documents, and more. Full support for both English and Chinese (中文) literature verification.
Verification Workflow
- Detect language: Determine if the reference is Chinese or English (or mixed)
- Parse the reference to extract structured fields (title, authors, year, journal/venue, DOI, URL, ISBN)
- Verify existence using appropriate sources:
- English: DOI → CrossRef; URL → HTTP check; title → CrossRef search
- Chinese: title → CNKI via Chrome CDP (primary), WebSearch (fallback); DOI → CrossRef (if available)
- Cross-check metadata between claimed and actual values
- Assess confidence and report findings
- Verify claims if the user asks about specific content attributed to the source
Verification by Identifier Type
Has DOI
Run scripts/verify_doi.py "<doi>". Compare returned metadata (title, authors, journal, year) against the user's citation. Flag any mismatch.
Has Title (No DOI)
Run scripts/search_crossref.py --title "<title>". If results return, compare the top match's metadata against the citation. If no match, try adding --author "<last_name>".
Has URL
Run scripts/verify_url.py "<url>". Check reachability, page title, and extracted metadata (citation_doi, citation_title, article_author). If URL is dead, suggest Wayback Machine: web.archive.org/web/<url>.
Has ISBN (Books)
Use WebSearch to query "ISBN <number>" site:openlibrary.org OR site:worldcat.org and verify the book record.
Minimal Information
Use WebSearch to search for the claimed title + author + year. Cross-reference results from Google Scholar (site:scholar.google.com), publisher sites, and library catalogs.
Chinese Literature Verification (中文文献核查)
Chinese literature requires different verification strategies because most Chinese publications are not indexed in CrossRef. 当 Chrome MCP 工具可用时，必须使用知网 CDP 直接检索作为首选核查方法；MCP 工具不可用时，以 WebSearch 作为备选。不得仅生成搜索链接或以"需知网核实"搪塞。每条中文文献必须给出明确判定。
What ships with it
10 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.
- literature-review-writer.skill 12 KB
- references/chinese-hallucination-patterns.md 3.0 KB
- references/chinese-verification-checklist.md 3.8 KB
- references/hallucination-patterns.md 3.0 KB
- references/verification-checklist.md 3.2 KB
- scripts/search_cnki.py 5.8 KB runs code
- scripts/search_crossref.py 3.6 KB runs code
- scripts/verify_chinese.py 9.9 KB runs code
- scripts/verify_doi.py 6.8 KB runs code
- scripts/verify_url.py 3.4 KB runs code
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.
- 11d ago First seen · 297 lines · 158 tokens per session scan A cddf370c111f
literature-verifier is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 158 tokens to every session and 4,271 once invoked, about $0.0008 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…