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 Mexregkan/claude-for-researchers --skill verify-citationgit clone --depth 1 https://github.com/Mexregkan/claude-for-researchersWrote 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/mexregkan/claude-for-researchers/verify-citation)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/verify-citation"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/verify-citation/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/mexregkan/claude-for-researchers/verify-citation"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/verify-citation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 37 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 38 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00031 | $0.00724 |
| Opus 5 | $0.00015 | $0.00362 |
| Sonnet 5 | $0.00006 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
verify-citation 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify-citation
Verify that a paper exists before writing it as a citation.
Inspired by the citation-verification patterns in flonat/claude-research and Imbad0202/academic-research-skills.
When to use
Run /verify-citation before writing any new citation into a .tex, .bib,
or .md file. If the user asks you to "add a reference to X", run this skill
first — do not write the citation until verification passes.
Usage
/verify-citation "Author, Title, Year"
/verify-citation "the paper we discussed about spectral geometry"
/verify-citation (no argument — verify all citations in the last assistant turn)
Steps
Step 1 — Extract the citation. If an argument is given, use it. Otherwise, extract every paper reference from the last assistant turn (titles, author–year pairs, DOIs, arXiv IDs).
Step 2 — Search. For each citation, search at least two of:
- arXiv:
https://arxiv.org/search/?searchtype=all&query=<title+author> - Semantic Scholar:
https://api.semanticscholar.org/graph/v1/paper/search?query=<title> - OpenAlex:
https://api.openalex.org/works?search=<title>
Use WebSearch or WebFetch to run the searches.
Step 3 — Report verdict.
| Result | Action |
|---|---|
| Found on 2+ sources, title and authors match | VERIFIED — write the citation |
| Found on 1 source, minor title variation | LIKELY — note the discrepancy, write with caution |
| Found on 0 sources, or title/author mismatch | UNVERIFIED — do NOT write the citation |
For UNVERIFIED: say "I cannot confirm this paper exists. Do you have a DOI or arXiv ID?" Do not invent an alternative. Do not write a citation that cannot be verified.
Step 4 — Write the citation (VERIFIED and LIKELY only). Use the metadata from the verified source (exact title, exact authors, correct year). Never reconstruct citation details from memory — use what the database returned.
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.
- 12d ago First seen · 78 lines · 31 tokens per session scan A 047ac53bc2ce
verify-citation is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 724 once invoked, about $0.0002 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
pre-submission-report
Run the final, comprehensive submission-readiness gate and consolidate all checks into one dated report; citation-integrity-only mode is also supported. Use when a paper and submission package are nearly final. Not for a mid-draft adversarial review; use $review-cluster.
proof-readability
Improve the exposition and readability of a mathematical proof already verified as correct without changing its mathematics. Use when polishing a lemma, theorem, proof, or appendix after correctness checks. Not for verifying the proof; use $verify-math.
latex
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…
beamer-deck
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
computational-experiments
Scaffold, execute, analyse, and publish computational research experiments through a reproducible staged workflow. Use when a research question requires simulations or computational sweeps rather than a one-off script.