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/danilkotelnikov/vedix/citatorgit clone --depth 1 https://github.com/danilkotelnikov/vedixWrote 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/danilkotelnikov/vedix/citator)<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/citator"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/citator.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 | $0.00034 | $0.01340 |
| Opus 5 | $0.00017 | $0.00670 |
| Sonnet 5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
vedix-citator 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citator
Fill citation gaps in references.bib. Every added citation is verified via the corpus acquisition pipeline (see mcp/lib/orchestrator/corpus_acquisition.py): DOI gate via Crossref + title-fuzzy ≥ 0.85, then OA-direct full-text acquisition to <output_dir>/.corpus/, then optional gentle Sci-Hub fallback when the orchestrator opts in. Citations whose DOI fails the gate or whose full-text cannot be obtained from any legitimate mirror are marked as "metadata-only" in the bib and downstream reviewer agents flag them.
Inputs
<input name="manuscript_tex"><input name="references_bib"><input name="max_rounds">— default 5<input name="use_scihub_fallback">— default false. When true, paywalled DOIs that fail OA-direct can be acquired via the patched Sci-Hub MCP at gentle pacing (≥ 25 sec/paper).
Steps
For each round (up to N):
- Read current manuscript + bib.
- Identify the most-needed missing citation. Categories:
- methods comparison
- background context
- tools/datasets cited
- WebFetch Semantic Scholar
https://api.semanticscholar.org/graph/v1/paper/search?query=<gap>&limit=5&fields=title,authors,year,doi,venue,abstract. Headerx-api-key: ${env:SEMANTIC_SCHOLAR_KEY}if set. - If found with valid metadata (title + ≥1 author + year + DOI), append BibTeX entry to references.bib. Note where it should be cited.
- If not found, skip and move to next gap.
- Stop early if no more gaps identified.
Rules
- Never fabricate metadata. If a search returns nothing, skip.
- Skip duplicates: check existing BibTeX keys before adding.
- Clean BibTeX: escape special LaTeX chars (
&→\&,{→\{,}→\}). - Strip accented chars from authors (e.g.,
Müller→Muller). - DOI gate is mandatory. Every new citation goes through
corpus_acquisition.CorpusAcquisitionPipeline.acquire_one(doi=..., title=..., year=..., discipline=...). The pipeline runscross_validator.stage1_doi_gate(Crossref + DataCite + title-fuzzy ≥ 0.85). Cite-without-fulltext entries are admissible but getvedix-metadata-onlyas an extra BibTeX field so reviewers know they couldn't be verified end-to-end. - Provenance is recorded. Successful acquisitions emit a
SourceLedger.record_call("oa_direct" | "scihub_mcp", success=True)entry and (if aKGStoreis attached to the job) a paper-skeletonKGFragmentis written to the per-job KG. The reviewer agent reads these back to confirm every claim has a citable paper Vedix actually obtained.
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.
- 4d ago First seen · 103 lines · 34 tokens per session scan A cc99ef420161
vedix-citator is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 1,340 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
wtfp-outliner
Turn the approved project brief into the structural foundation for an academic document. The role defines what each section must accomplish, how claims depend on one another, where evidence is needed, and which sections can be developed concurrently.
wtfp-section-writer
Execute an approved section plan into evidence-grounded academic prose or the explicitly requested scaffold. Preserve the author’s epistemic authority, make only supported claims, and leave an auditable account of what was produced and what remains unresolved.
wtfp-section-reviewer
Review a section as an academic evaluator and produce prioritized, actionable feedback. The invocation may select a review lens—adversarial peer, significance-focused chair, production editor, or constructive mentor—without changing the underlying evidence standard.
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.