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 ShaishavMaisuria/research-paper-lifecycle-skills --skill verify-citationsgit clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-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/shaishavmaisuria/research-paper-lifecycle-skills/verify-citations)<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/verify-citations"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/verify-citations/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/shaishavmaisuria/research-paper-lifecycle-skills/verify-citations"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/verify-citations.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 | $0.00140 | $0.03556 |
| Opus 5 | $0.00070 | $0.01778 |
| Sonnet 5 | $0.00028 | $0.00711 |
| Haiku 4.5 | $0.00014 | $0.00356 |
Grade A, and why
verify-citations 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Citations
The anti-hallucination gate for bibliographies. Takes a .bib file, validates
every entry against live scholarly indexes (Crossref, DBLP, Semantic Scholar,
arXiv, DataCite), and produces a per-entry verdict: VERIFIED, MISMATCH,
UNRESOLVED (possible fabrication), or RETRACTED. One fabricated citation in a
submitted paper can end a review — or a reputation. Be rigorous here.
Resolving is necessary but not sufficient. An identifier that resolves only proves the entry points at a real record — not that it is the right instance of the named work, nor that an independently-added reference is even on-topic. The gate therefore goes beyond resolution with two non-fabricating heuristics: a canonical-instance check (when a title exists as both, say, a conference paper and a later RFC/tech-report/preprint, surface the alternatives with citation counts so you cite the artifact the field cites) and an opt-in relevance gate (score an added reference's topical fit and flag low-fit ones for human review). And when an authoritative index is unreachable, the run reports PARTIAL-PASS, never a clean PASS, naming the checks that did not run — so "could not check" is never mistaken for "checked and clean".
When to use
- The user asks to verify, check, validate, or audit citations / references /
a bibliography / a
.bibfile. - Any writing skill (
draft-related-work,literature-review,write-rebuttal, ...) added or edited citations — run this gate before declaring that work done. - Before
preflight-check/ submission, camera-ready, or arXiv upload. - The user suspects AI-generated references ("are these real papers?").
Inputs
- A
.bibfile (path from the user, or find it:*.bibnext to the main.tex, or the file named in\bibliography{...}/\addbibresource{...}). CONTACT_EMAILenvironment variable — a real email, sent in the User-Agent so API providers can contact instead of block. Ask the user for it if unset; never invent one.- Optional:
S2_API_KEYfor a dedicated Semantic Scholar rate allowance (the shared anonymous pool 429s under load; the script backs off and falls back to other providers automatically).
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.
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 · 233 lines · 140 tokens per session scan A d6e96ee70810
verify-citations is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 3,556 once invoked, about $0.0007 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
aaai-reproducibility
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that Phase-1 reviewers use to judge rigor across…
aaai-submission
Use when auditing an AAAI main technical track submission for OpenReview readiness, double-blind anonymity, page limits, reproducibility checklist, supplementary material, author limits, multiple-submission policy, and AAAI AI-use policy compliance.
acl-author-response
Use when drafting an ACL author response inside an ACL Rolling Review cycle on OpenReview, covering the response window before meta-review, reviewer discussion dynamics, score-change strategy, flagging review issues to the area chair, anonymity rules, and deciding between responding now versus revising for a later ARR…
acl-camera-ready
Use when preparing an accepted ACL main-conference or Findings paper for camera-ready, covering the extra content page, de-anonymization and acknowledgements, AI-assistance disclosure, keeping the Limitations section, ACL Anthology metadata and CC BY 4.0 publication, meta-review-driven edits, and presentation-mode…
acl-related-work
Use when positioning an ACL submission against the NLP literature, covering ACL Anthology citation practice, arXiv-versus-published version citation, concurrent LLM-era preprints, prior-cycle ARR resubmission overlap, anonymity-preserving self-citation, and the fast-moving baseline problem in computational linguistics.
acl-reproducibility
Use when strengthening reproducibility evidence for an ACL paper reviewed through ACL Rolling Review, covering the Responsible NLP checklist end to end, hyperparameter and compute reporting, prompt and decoding disclosure for LLM experiments, data contamination auditing, variance across runs, and checklist-to-paper…