dvcon

dvcon is a command for coding agents from hevangel/dvcon_ai_library. It costs 26 tokens per session (359 once invoked), scanned A, original, MIT.

A command for searching DVCon, a conference paper archive focused on electronic design and verification, and answering with citations.

In plain words
What is it for?
Search by topic, browse or filter papers by year and location, retrieve a named paper, and request cited summaries or comparisons.
Why use it?
It provides a direct way to find relevant papers and trace answers back to specific sources.

Command

Part of the dvcon-papers plugin — 1 skill, 1 command shipped together

Install

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.

agentmods
npx agentmods add commands/hevangel/dvcon_ai_library/dvcon
Clone the repo
git clone --depth 1 https://github.com/hevangel/dvcon_ai_library

Or install dvcon-papers, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Wrote 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.

agentmods badge for dvcon

README.md
[![agentmods](https://agentmods.dev/badge/commands/hevangel/dvcon_ai_library/dvcon.svg)](https://agentmods.dev/commands/hevangel/dvcon_ai_library/dvcon)
Your own site
<a href="https://agentmods.dev/commands/hevangel/dvcon_ai_library/dvcon"><img src="https://agentmods.dev/badge/commands/hevangel/dvcon_ai_library/dvcon.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00359
Opus 5 $0.00013 $0.00179
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 5d ago against content hash 7fb2ce402027, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dvcon 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.

plugins/dvcon-papers/commands/dvcon.md · 22 lines

What it actually says

Use the dvcon MCP server tools to handle this request against the DVCon paper corpus:

$ARGUMENTS

Follow this flow:

  1. If the request looks like a search or topic question, call dvcon__search_papers with the query (hybrid mode by default). Present the top results as a numbered list with paper_id, title, year, location, and a one-line snippet.
  2. If the request names or implies a specific paper, call dvcon__get_paper_detail and dvcon__get_paper_markdown for that paper_id and answer from the extracted content.
  3. If the request asks for synthesis, comparison, or summarization across one or more papers, call dvcon__chat_with_papers with the resolved selected_paper_ids and the user's question. Cite claims with the returned [n] citation labels.
  4. If the request asks for corpus size or coverage, call dvcon__corpus_stats.

Rules:

  • Always cite the paper_id (and title + year when space allows) when referencing a paper.
  • If a tool returns an error field, surface that error verbatim instead of fabricating content.
  • Never invent DVCon paper content that did not come back from a tool call.
Changes

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.

  1. 5d ago First seen · 22 lines · 26 tokens per session scan A 7fb2ce402027

Subscribe to this mod's changes

dvcon is a command published in the GitHub repository hevangel/dvcon_ai_library (11 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 359 once invoked, about $0.0001 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 2026-08-30.