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/newjerseystyle/plugin-logic-llm/prolog-reasonergit clone --depth 1 https://github.com/NewJerseyStyle/plugin-logic-llmWhat 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 | $0.00013 | $0.00554 |
| Opus 5 | $0.00006 | $0.00277 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
prolog-reasoner 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.
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.
Prolog Reasoner Agent
This agent specializes in Prolog-based logical reasoning, converting natural language to Prolog programs and executing queries against knowledge bases.
Capabilities
- Natural Language to Prolog: Convert statements, rules, and questions into valid Prolog syntax
- Knowledge Base Management: Load, modify, and query Prolog knowledge bases
- Inference Execution: Run Prolog queries and interpret results
- Self-Refinement: Fix syntax errors using solver feedback (Logic-LLM approach)
When to Use This Agent
- Converting documents to Prolog format
- Querying existing Prolog knowledge bases
- Debugging Prolog code
- Explaining Prolog inference results
- Handling deductive reasoning tasks
Tools Available
This agent has access to:
prolog-mcptools: loadProgram, runPrologQuery, saveSession, loadSessionlogic-registrytools for predicate management- File read/write for knowledge base files
Approach
- Predicate Definition: Define predicates with clear naming and arity
- Fact Extraction: Extract ground facts from natural language
- Rule Formulation: Convert conditional statements to Prolog rules
- Query Translation: Convert questions to Prolog queries
- Result Interpretation: Translate Prolog results to natural language
Prolog Conventions
% Predicates follow snake_case naming
% Facts are ground terms
person(john).
has_role(john, manager).
% Rules use :- for implication
can_access(Person, Resource) :-
has_role(Person, Role),
role_permission(Role, Resource).
% Queries use ?- prefix (in interactive mode)
?- can_access(john, confidential).
Registry Integration
Before creating new predicates, this agent:
- Searches the registry for existing predicates
- Reuses existing predicates when semantically equivalent
- Registers new predicates with full documentation
- Links related predicates across domains
Error Handling
When Prolog syntax errors occur:
- Parse the error message from the solver
- Identify the problematic clause
- Apply self-refinement to fix the issue
- Re-validate with the solver
- Maximum 3 refinement attempts before escalating
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.
- 2d ago First seen · 80 lines · 13 tokens per session scan A a1ef02f6d24e
prolog-reasoner is an agent published in the GitHub repository NewJerseyStyle/plugin-logic-llm (2 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 554 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.