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 skills add jabrena/plinth --skill 033-architecture-diagramsgit clone --depth 1 https://github.com/jabrena/plinthWrote 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/jabrena/plinth/033-architecture-diagrams)<a href="https://agentmods.dev/skills/jabrena/plinth/033-architecture-diagrams"><img src="https://agentmods.dev/badge/skills/jabrena/plinth/033-architecture-diagrams/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/jabrena/plinth/033-architecture-diagrams"><img src="https://agentmods.dev/badge/skills/jabrena/plinth/033-architecture-diagrams.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 | $0.00117 | $0.02579 |
| Opus 5 | $0.00059 | $0.01290 |
| Sonnet 5 | $0.00023 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
033-architecture-diagrams 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 11d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Diagrams Generator with modular step-based configuration
Generate comprehensive Java project diagrams through a modular, step-based interactive process that covers UML sequence diagrams, UML class diagrams, C4 model diagrams, UML state machine diagrams, UML Deployment Diagrams, ER (Entity Relationship) diagrams, and bounded-context diagrams using PlantUML syntax. This is an interactive SKILL.
What is covered in this Skill?
- UML sequence diagram generation for application workflows and API interactions
- UML class diagram generation for package structure and class relationships
- C4 model diagram generation for Context, Container, and Component diagrams
- UML state machine diagram generation for entity lifecycles and business workflows
- UML Deployment Diagram generation for runtime topology, nodes, execution environments, deployed components, data stores, queues, external systems, and communication paths
- ER diagram generation from SQL schema (DDL, migrations) using PlantUML Chen notation
- Bounded-context diagram generation for DDD context maps across one or more repositories
- PlantUML syntax for all diagram types
- File organization strategies: single-file, separate-files, or integrated with existing documentation
- Final diagram validation with PlantUML syntax checking
- PlantUML validation and PNG/SVG rendering with a trusted local PlantUML installation or repository-approved wrapper
Constraints
Before applying any diagram generation, ensure the project validates. If validation fails, stop immediately — do not proceed until all validation errors are resolved.
- MANDATORY: Run
./mvnw validateormvn validatebefore applying any diagram generation - SAFETY: If validation fails, stop immediately — do not proceed until all validation errors are resolved
- BEFORE READING DIAGRAM REFERENCES: Run the question flow embedded in this SKILL.md first. Ask the diagram preference questions one by one, collect selected diagram families and output preferences, then read only the implementation references selected by the user's answers
- C4 SCOPE: C4 diagrams are restricted to Context, Container, and Component diagrams
- SUPPLY CHAIN: Generated PlantUML diagrams must use trusted local includes only; do not use remote
!includeURLs for C4 or icon libraries - TOOLING SAFETY: Use only trusted local PlantUML tooling or a repository-approved wrapper; do not pull or run remote container images as part of this skill
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/033-architecture-diagrams-bounded-context.md 8.4 KB
- references/033-architecture-diagrams-c4.md 14 KB
- references/033-architecture-diagrams-deployment.md 9.3 KB
- references/033-architecture-diagrams-er.md 14 KB
- references/033-architecture-diagrams-state-machine.md 11 KB
- references/033-architecture-diagrams-uml-class.md 12 KB
- references/033-architecture-diagrams-uml-sequence.md 11 KB
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.
- 11d ago First seen · 275 lines · 117 tokens per session scan A 43de313d2770
033-architecture-diagrams is a skill published in the GitHub repository jabrena/plinth (438 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 2,579 once invoked, about $0.0006 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.
Other skills, from other repositories
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
prompt-engineering
A deep, practical guide to engineering reliable LLM prompts — role/context, instructions, few-shot, structured output, chain-of-thought, delimiting untrusted data, injection defense, and evaluation. Includes worked prompts and a runnable output validator.
searchcans-rag-source-curator-zh
A Chinese-language tool for building a small, varied list of web pages and documents that can support answers in a retrieval-augmented generation (RAG) system. RAG systems retrieve source material to ground an AI response.
knowledge-graph-extract
Use when the user wants to extract a knowledge graph, entities and relationships, or subject-relation-object triplets from a folder of documents or a set of files — including resuming an interrupted extraction, or turning extracted triplets into Cypher import scripts for Neo4j/Memgraph.
optuna-hyperparameter-tuning
When the user wants to tune metaheuristic or solver parameters with Optuna, including search-space definition, TPE sampling, pruning weak configurations early, multi-instance objectives (mean/median over an instance set), and held-out validation against overtuning. Also use when the user mentions "Optuna,"…
prompt-analyzer
Analyze prompts for constraint complexity, audit failure risks, and generate optimized rewrites for Claude and GPT. Based on "How LLMs Follow Instructions" (Rocchetti & Ferrara, 2026) constraint taxonomy research. Use when reviewing prompt files, optimizing prompt bases, or auditing instruction quality. Trigger…