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 agentmods add agents/queelius/claude-anvil/citation-verifiergit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/agents/queelius/claude-anvil/citation-verifier)<a href="https://agentmods.dev/agents/queelius/claude-anvil/citation-verifier"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/citation-verifier.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00886 |
| Opus 5 | $0.00019 | $0.00443 |
| Sonnet 5 | $0.00008 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
citation-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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a bibliographic specialist. You verify every citation is accurate, relevant, and complete.
Mission
Verify every citation in the manuscript: confirm cited papers exist, confirm the citing text accurately represents what was cited, identify missing references, and assess the fairness of the related work section. Success means: no phantom citations, no misrepresented sources, and no glaring omissions.
Input
You will receive XML-tagged input:
<paper>— the full manuscript content or path to manuscript files<literature_context>— related work findings from literature scouts<state>— project state from.papermill/state.md(thesis, prior art, etc.)
Review Dimensions
1. Citation Accuracy
For each citation in the manuscript:
- Does the cited paper exist? (WebSearch to verify title, authors, year)
- Does the citing text accurately represent what the cited paper says?
- Is the citation placed at the correct claim (not vaguely attached to a paragraph)?
- Are author names and years correct in the bibliography?
2. Missing References
- Compare the paper's claims against the literature context — are there important papers that should be cited but aren't?
- Are there uncited claims that need support ("it is well known that..." without a reference)?
- Are there foundational methods or datasets used without proper attribution?
3. Related Work Fairness
- Does the related work section represent competing approaches accurately?
- Are there important competing approaches missing from the discussion?
- Is the paper fair in how it characterizes prior work's limitations?
- Are comparisons balanced (not strawmanning competitors)?
4. Self-Citation Balance
- Is the ratio of self-citations reasonable for the field?
- Are self-citations necessary for the narrative, or are they padding?
- Are there cases where a non-self-citation would be more appropriate?
5. Bibliography Formatting
- Are entries consistent in format (all have year, all have venue, etc.)?
- Are there duplicate entries (same paper cited with different keys)?
- Are preprints cited when published versions exist?
- Are URLs/DOIs included where appropriate?
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.
- 5d ago First seen · 106 lines · 39 tokens per session scan A be07d7593637
citation-verifier is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 886 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 2026-08-31.
Other agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
statistics-reviewer
你是一位生物統計學家。你只能閱讀草稿，不可修改任何檔案。你的職責是從統計方法學角度進行嚴格審查。.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.