Borrowing it
Nothing to install: this file belongs to hevangel/dvcon_ai_library. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hevangel/dvcon_ai_library/main/.agents/skills/dvcon-papers/SKILL.mdgit clone --depth 1 https://github.com/hevangel/dvcon_ai_libraryWrote 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/hevangel/dvcon_ai_library/dvcon-papers)<a href="https://agentmods.dev/skills/hevangel/dvcon_ai_library/dvcon-papers"><img src="https://agentmods.dev/badge/skills/hevangel/dvcon_ai_library/dvcon-papers/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/hevangel/dvcon_ai_library/dvcon-papers"><img src="https://agentmods.dev/badge/skills/hevangel/dvcon_ai_library/dvcon-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01395 |
| Opus 5.5 | $0.00052 | $0.00558 |
| Sonnet 5.5 | $0.00026 | $0.00279 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
dvcon-papers 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 2mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DVCon Papers
This skill gives the agent direct access to the local DVCon paper corpus through the
dvcon MCP server (defined in backend/src/backend/mcp_server.py). The corpus is the
same one served by the FastAPI backend and React UI; the MCP server just re-exposes it
as tools so agents can query it without going over HTTP.
When to use
Trigger this skill when the user wants to:
- search the DVCon proceedings by keyword, topic, author, method, or concept
- read a specific paper's extracted markdown or full metadata
- summarize one paper or compare several papers
- look at the author / conference / company / reference graph for a paper
- ask a grounded question whose answer must come from the indexed papers
- get corpus counts (how many papers, years, locations)
Prerequisites
The dvcon MCP server must be configured in the client's MCP settings and pointed at
uv run --project backend dvcon-mcp (stdio). The corpus lives under data/ and is
configured via .env. The read tools (search, detail, markdown, graph, stats) work
without GROBID or OpenAI. The chat_with_papers tool requires OPENAI_BASE_URL and
OPENAI_API_KEY.
If the corpus is empty, seed it first with uv run --project backend ingest --limit 5
(or the /api/admin/ingest endpoint), then re-run search.
Available tools
| Tool | Purpose |
|---|---|
search_papers |
Keyword / semantic / hybrid search with year + location filters |
get_paper_detail |
Full metadata for one paper (abstract, authors, affiliations, references) |
get_paper_markdown |
Extracted markdown body of a paper (includes image refs) |
get_paper_graph |
Cytoscape-style nodes/edges for paper relationships |
corpus_stats |
Paper count, years, locations, conference count |
chat_with_papers |
Grounded Q&A; constrain to selected paper ids when comparing |
Workflows
1. Find papers on a topic
Call search_papers with a free-text query. Hybrid mode (default) merges SQLite FTS5
keyword hits with bge-m3 semantic hits. Example call:
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.
- 2mo ago First seen · 147 lines · 131 tokens per session scan A 532f447cf4fe
dvcon-papers is a skill published in the GitHub repository hevangel/dvcon_ai_library (11 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 1,395 once invoked, about $0.0005 per session on Opus 5.5. 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.
dvcon-papers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dvcon-papershevangel/dvcon_ai_library | Skill | 11 | 2mo ago | MIT | A | 131 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |