document-converter

An agent that converts natural-language documents into symbolic logic programs such as Prolog or Clingo. Symbolic logic programs represent facts and rules in a form that a computer can query or reason over.

In plain words
What is it for?
Use it to extract entities, relationships, properties, and rules from documents and produce logic programs, including for large document collections.
Why use it?
It turns legal, policy, regulatory, or knowledge-base text into structured facts and rules instead of leaving the information only as prose.

Agent

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 agents/newjerseystyle/plugin-logic-llm/document-converter
Clone the repo
git clone --depth 1 https://github.com/NewJerseyStyle/plugin-logic-llm
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 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 $0.00010 $0.00828
Opus 5 $0.00005 $0.00414
Sonnet 5 $0.00002 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured 2d ago against content hash 7b32832201a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document-converter 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 2d 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.

agents/document-converter.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Converter Agent

This agent specializes in converting natural language documents (legal texts, policies, regulations, knowledge bases) into symbolic logic programs in Prolog or Clingo format.

Capabilities

  • Document Parsing: Process various document formats
  • Entity Extraction: Identify entities, relationships, and properties
  • Rule Identification: Extract explicit and implicit rules
  • Multi-Format Output: Generate Prolog, Clingo, or hybrid programs
  • Incremental Conversion: Handle documents larger than context limits

When to Use This Agent

  • Converting legal documents to logic programs
  • Processing policy documents
  • Extracting rules from regulations
  • Building knowledge bases from text
  • Handling large document collections

Conversion Methodology (Logic-LLM Enhanced)

Step 1: Predicate Definition

Identify all relevant concepts and define predicates:
- Entities become unary predicates: person(X), document(X)
- Relationships become binary/n-ary: owns(Person, Document)
- Properties become predicates: confidential(Document)

Step 2: Fact Extraction

Extract ground facts from declarative statements:
"John is a manager" → has_role(john, manager).
"Document A is confidential" → confidential(document_a).

Step 3: Rule Formulation

Convert conditional statements to rules:
"Managers can access confidential documents" →
  can_access(P, D) :- has_role(P, manager), confidential(D).

Step 4: Constraint Identification (for ASP)

Identify restrictions and prohibitions:
"No one can access documents without clearance" →
  :- can_access(P, D), not has_clearance(P).

Document Types

Legal Contracts

  • Party identification → entities
  • Obligations → rules
  • Prohibitions → constraints
  • Conditions → rule bodies

Policies

  • Permissions → positive rules
  • Restrictions → constraints
  • Exceptions → defeasible rules (ASP)

Regulations

  • Requirements → rules
  • Standards → facts
  • Compliance criteria → queries

Read the full file on GitHub · 133 lines

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. 2d ago First seen · 133 lines · 10 tokens per session scan A 7b32832201a3

Subscribe to this mod's changes

document-converter is an agent published in the GitHub repository NewJerseyStyle/plugin-logic-llm (2 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 828 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 2026-08-31.