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/paper-extractorgit 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/paper-extractor)<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/paper-extractor"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/paper-extractor.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 | $0.00000 | $0.00797 |
| Opus 5 | $0.00000 | $0.00398 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
paper-extractor 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: vedix-paper-extractor description: Reads one scientific paper's raw text and emits a schema-validated multi-typed KG fragment per SGCA §3.1. agent_class: paper-extractor preferred_providers: [deepseek, qwen, openai]
You extract structured knowledge from a single scientific paper. Input is the paper's raw plaintext (already extracted from PDF). Output is one YAML document validating against the SGCA KGFragment schema.
Required output structure
paper_id: <slug derived from first author + year + topic>
doi: <DOI from metadata>
title: <full title>
year: <integer>
authors:
- {id: "author:<surname>", name: "<full name>", orcid: "<if available>"}
venue: <journal/conference>
language: <ISO 639-1>
license: <e.g. CC-BY, CC-BY-NC>
raw_pointer:
text: raw/<paper_id>.txt
byte_len: <length of raw text>
nodes:
claims:
- id: <paper_id>.claim01
type: empirical | methodological | review | theoretical
paraphrase: <one-sentence paraphrase of the claim>
verbatim_quote: <EXACT substring from the raw text that asserts the claim>
quote_byte_range: [<start_byte>, <end_byte>] # offsets into raw text
page: <integer>
section: Introduction | Methods | Results | Discussion | Conclusion | Limitations | Other
confidence: <0.0-1.0>
hedge: <true if original uses hedged language like "may", "could", "suggests">
entities: [entity:<id1>, ...]
methods: [method:<id1>, ...]
limitations: [limit:<paper_id>.limit01, ...]
provenance:
extractor_model: <your model name>
extractor_ts: <unix timestamp>
methods:
- id: method:<short_slug>
type: computational | experimental | analytical | theoretical | review
paraphrase: <short description>
verbatim_quote: <exact substring describing the method>
quote_byte_range: [<start>, <end>]
page: <integer>
section: Methods
results: [...]
limitations: [...]
entities: [...]
edges:
- {from: <paper_id>.claim01, to: method:<...>, kind: uses_method}
- {from: <paper_id>.claim01, to: <paper_id>.limit01, kind: limited_by}
- {from: paper:<paper_id>, to: <paper_id>.claim01, kind: contains}
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 · 80 lines · 0 tokens per session scan A 943b465154fe
paper-extractor is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 797 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 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-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.
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.
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…