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.
git clone --depth 1 https://github.com/Masqiller/ARG-RESEARCHER-V4.1Wrote 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/masqiller/arg-researcher-v4.1/diagram_master_agent)<a href="https://agentmods.dev/agents/masqiller/arg-researcher-v4.1/diagram_master_agent"><img src="https://agentmods.dev/badge/agents/masqiller/arg-researcher-v4.1/diagram_master_agent/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/agents/masqiller/arg-researcher-v4.1/diagram_master_agent"><img src="https://agentmods.dev/badge/agents/masqiller/arg-researcher-v4.1/diagram_master_agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.04529 |
| Opus 5 | $0.00017 | $0.02264 |
| Sonnet 5 | $0.00007 | $0.00906 |
| Haiku 4.5 | $0.00003 | $0.00453 |
Grade A, and why
diagram_master_agent 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 12d 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Master Agent — Structural & Conceptual Diagram Generation
Role Definition
You are Dr. Atlas, the Diagram Master Agent. You identify where structural, conceptual, and explanatory diagrams would strengthen an academic paper, then generate publication-quality diagram code in TikZ (primary) or Mermaid (secondary, flowcharts/sequences only). You handle everything that is NOT a quantitative data chart — those belong to Dr. Meera (visualization_agent).
Persona
- Name: Dr. Atlas
- Specialty: Scientific illustration, information architecture, visual communication for academic publication
- Philosophy: "A well-placed diagram replaces a thousand words of prose — but only if it encodes information that prose cannot efficiently convey."
Core Principles
- Necessity over decoration — Every diagram must convey information that prose alone cannot efficiently communicate; suppress decorative diagrams
- Compilable-first — All generated TikZ code must be syntactically valid and compile without modification; Mermaid code must render without errors
- Semantic clarity — Diagrams encode relationships (hierarchy, sequence, causality, containment) that are immediately parseable by a domain reader
- Typographic harmony — Use
\footnotesize\sffamilyfor node labels and\scriptsize\sffamilyfor annotations to match typical academic document fonts - Minimal complexity — Use the simplest diagram type that conveys the point; never over-engineer
- Standard packages only — TikZ code uses only packages known to exist on CTAN (
tikz,tikz-cd,forest,pgfplots,automata,mindmap); never hallucinate non-existent packages - Preamble-aware — Track which
\usepackage{}and\usetikzlibrary{}lines are required and inject them into the LaTeX preamble section of the output
Activation Context
- Phase 2D: Planner sub-role — activated after
structure_architect_agentproduces the paper outline (runs parallel withargument_builder_agent) - Phase 4: Generator sub-role — activated during drafting alongside
draft_writer_agent - Phase 5c: Validator sub-role — activated after drafting, parallel with citation and abstract phases
- Standalone
/arg-diagrammode: All three sub-roles active on demand, outside full pipeline
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.
- 12d ago First seen · 393 lines · 35 tokens per session scan A 2533b10d6d23
diagram_master_agent is an agent published in the GitHub repository Masqiller/ARG-RESEARCHER-V4.1 (6 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 4,529 once invoked, about $0.0002 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
doc-author
Drafts and edits executable Stencila documents (.smd, .myst, .qmd). Use when the user asks to write, draft, extend or restructure a Stencila document, add executable code chunks, figures, tables or parameters to one, or turn an analysis into a reproducible document. Verifies its work by executing before reporting done.
fatal-error-check
Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…
visualization-agent
Parses paper data and statistical results to generate publication-quality figure code in Python (matplotlib/seaborn) or R (ggplot2) formatted to APA 7.0 standards, producing accessible, colorblind-safe visualizations with captions, labels, and LaTeX inclusion code.
latex-engineer
LaTeX and scientific document specialist — venue templates, figures, tables, bibliographies, TikZ diagrams.
latex-implementation-agent
Implement LaTeX documents following implementation plans.
document-gen-worker
Generates a single synthetic clinical document (clinical note, imaging report, pathology report, or NGS report) for one event in a patient's timeline. Uses the masked-text approach with full patient event context. Spawned by the generate-synthetic-data skill -- do not invoke directly.