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 muhammad1438/academic-writer-skills --skill reference-verifiergit clone --depth 1 https://github.com/muhammad1438/academic-writer-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/muhammad1438/academic-writer-skills/reference-verifier)<a href="https://agentmods.dev/skills/muhammad1438/academic-writer-skills/reference-verifier"><img src="https://agentmods.dev/badge/skills/muhammad1438/academic-writer-skills/reference-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/muhammad1438/academic-writer-skills/reference-verifier"><img src="https://agentmods.dev/badge/skills/muhammad1438/academic-writer-skills/reference-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 | $0.00000 | $0.02698 |
| Opus 5.5 | $0.00000 | $0.01079 |
| Sonnet 5.5 | $0.00000 | $0.00540 |
| Haiku 4.5 | $0.00000 | $0.00270 |
Grade A, and why
reference-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 1mo 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Verifier
Citation verification is a mandatory step before submission. Errors in reference lists undermine credibility and can delay publication. The rise of AI-generated text has introduced a new category of fabricated citations that appear plausible but are entirely non-existent.
Why Reference Verification Is Critical
Accuracy: A single wrong page number, volume, or year signals carelessness to reviewers. Systematic errors suggest fabrication.
Retraction risk: Citing a retracted paper without noting the retraction can constitute a serious integrity breach. Thousands of papers are retracted annually.
AI hallucination: Large language models regularly generate plausible-sounding but entirely fictional citations — correct author names, realistic journal names, plausible years, and fabricated DOIs. These require verification before use.
Orphan and phantom references: Orphan = cited in text but missing from the reference list. Phantom = in the reference list but never cited in the text. Both are submission errors.
Self-citation ethics: Excessive self-citation is flagged by editors. Cite your own work only when directly relevant, not routinely.
Reference Error Types
| Error Type | Description | How to Detect | How to Fix |
|---|---|---|---|
| AI hallucination | Entirely fabricated citation that does not exist | Search DOI + title in CrossRef/Google Scholar | Remove; find a real source or remove the claim |
| Wrong DOI | Doi resolves to a different paper | Resolve doi.org/[DOI] in browser | Locate correct DOI via CrossRef |
| Wrong page range | Listed pages differ from published article | Check via DOI or journal website | Correct from journal website |
| Wrong year | Publication year incorrect | CrossRef lookup | Correct from official source |
| Wrong volume/issue | Volume or issue number wrong | Journal website or DOI | Correct from official source |
| Retracted paper | Paper has been retracted post-publication | RetractionWatch; PubMed retraction notices | Remove or replace; if citing, note retraction |
| Author name error | First/last name swapped; misspelled | CrossRef or PubMed lookup | Correct to match published version |
| Missing DOI | DOI not included (increasingly required) | CrossRef.org lookup | Add DOI |
| Orphan citation | Cited in text, absent from reference list | Cross-check text citations vs. list | Add full reference |
| Phantom reference | In reference list, not cited in text | Cross-check list vs. text citations | Remove or add in-text citation |
| Non-existent journal | Journal name does not exist | Google the journal | Flag as likely hallucination; verify source |
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.
- 1mo ago First seen · 255 lines · 0 tokens per session scan A 24bc4fdc7b01
reference-verifier is a skill published in the GitHub repository muhammad1438/academic-writer-skills (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,698 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 2026-08-31.
Other skills, from other repositories
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
audit
Check thesis chapters for consistency before submission — contradictory numbers, terminology drift, and broken cross-references — and read every rewritten or proposed sentence against the one it replaces before anyone sees the rewrite.
argument-governance
Build and audit the manuscript or research-project argument system across intended use, gaps, claims, data, results, experiment roles, contributions, innovation evidence, limitations, and contribution focus. Use when a paper, thesis chapter, review article, or research project needs an explicit argument map…
readers
Open a reader panel. Instruction-bound amnesiac sub-agents read the abstract or introduction and report what they carried away, set against the author's intended points. Use when those sections change or the writing loop marks the panel stale.
self-review
Review the user's own manuscript, paper, thesis chapter, rebuttal, or release packet with clean-room anti-contamination controls and, when needed, an unfamiliar-reader comprehension gate. Use for internal review, readiness checks, reviewer simulation, or claim-evidence self-audit where prior chat memory and unstated…