agentmods.dev

java-code-to-erd

java-code-to-erd is a skill for Codex from cocoCzl/coco-skills. It costs 89 tokens per session (803 once invoked), scanned A, original, MIT.

A source-code analysis tool that reconstructs the database structure represented by a Java project and produces an entity-relationship diagram, DBML, and written reports. An entity-relationship diagram shows tables and their relationships; DBML is a text format for describing database models.

In plain words
What is it for?
Use it to find tables, columns, and relationships from Java classes, ORM mappings, SQL, database definitions, Flyway, and Liquibase files. It is for repository analysis, not live database inspection.
Why use it?
It documents the database model without connecting to a live database or running the project. Evidence, uncertainty, and conflicting definitions remain visible instead of being presented as facts without support.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 5repo changed 16d ago A scan 89 tokens original MIT

Good fit Use it to find tables, columns, and relationships from Java classes, ORM mappings, SQL, database definitions, Flyway, and Liquibase files. It is for repository analysis, not live database inspection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cococzl/coco-skills/java-code-to-erd
View source ↗ cocoCzl/coco-skills
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.

Any agent
npx skills add cocoCzl/coco-skills --skill java-code-to-erd
Clone the repo
git clone --depth 1 https://github.com/cocoCzl/coco-skills

Made for: Codex.

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 java-code-to-erd

README.md
[![agentmods](https://agentmods.dev/badge/skills/cococzl/coco-skills/java-code-to-erd/github.svg)](https://agentmods.dev/skills/cococzl/coco-skills/java-code-to-erd)
Your own site
<a href="https://agentmods.dev/skills/cococzl/coco-skills/java-code-to-erd"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/java-code-to-erd/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.

agentmods 80×15 button for java-code-to-erd

Your own site · 80×15
<a href="https://agentmods.dev/skills/cococzl/coco-skills/java-code-to-erd"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/java-code-to-erd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00089 $0.00803
Opus 5.5 $0.00036 $0.00321
Sonnet 5.5 $0.00018 $0.00161
Haiku 4.5 $0.00009 $0.00080

Measured 16d ago against content hash b02321eb6fdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

java-code-to-erd 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 16d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/java_code_to_erd.py, scripts/launch.py, scripts/lib/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

java-code-to-erd/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Java Code to ERD

Reconstruct the database model expressed by a Java repository. The result describes project evidence, not a live database.

Non-negotiable boundaries

  • Never connect to a database, execute SQL or migrations, build/run the target project, access the network, or install software.
  • Analyze repository source and project files only. Exclude tests, examples, build outputs, dependencies, external JARs, and paths outside the project unless the user explicitly includes test sources.
  • Do not infer a confirmed relation from names alone. Preserve unknowns, conflicts, conditional facts, and unsupported constructs.
  • Generate every artifact from the validated database-model.json; never produce an ERD directly from an ad-hoc reading.
  • Evidence stores project-relative path and line range only—no source snippets.

Workflow

Read references/workflow.md, references/data-model.md, and references/confidence-and-conflicts.md for every analysis.

  1. Run analyze directly through the compatibility launcher; use doctor only for capability questions or actual environment errors. It selects an already-installed Python 3.10+ and never installs one:

    python3 <skill-dir>/scripts/launch.py analyze --project <project-root>

  2. Read only the detected framework rules listed in the result's rule_references.

  3. Inspect unresolved and conflicts. Use repository reading to resolve only what static evidence supports; record manual confirmations with review, never by editing generated facts.

  4. Re-run analysis after review or scoped inspection.

  5. If Mermaid SVGs were produced, inspect them for clipping, overlap, density, labels, direction, and legend. Read references/output-and-visual-quality.md. After every generated SVG passes that inspection, run verify-visuals --project <project-root> so the model and report record VERIFIED. Never run this command before actually viewing all SVGs.

  6. Report COMPLETE only when the model validates and no material file, unsupported data path, unresolved construct, or conflict remains. Otherwise report PARTIAL; use FAILED only when no valid core model can be produced.

Read the full file on GitHub · 45 lines

Files

What ships with it

24 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.

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. 16d ago Changed · +1 lines b02321eb6fdb
  2. 2mo ago First seen · 44 lines · 89 tokens per session scan A 4f7f3fe36aec

Subscribe to this mod's changes

java-code-to-erd is a skill published in the GitHub repository cocoCzl/coco-skills (5 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 803 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-05.

DatabasesJavaLanguages
Related

java-code-to-erd compared with skills from other repositories

java-code-to-erd next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
java-code-to-erdcocoCzl/coco-skillsSkill516d agoMITA89Codex
jpa-patternsaffaan-m/ECCSkill299kyesterdayMITA33Claude Code, Kiro
azure-data-tables-javamicrosoft/skillsSkill3.2kyesterdayMITA47Claude Code
azure-cosmos-javamicrosoft/skillsSkill3.2kyesterdayMITA59Claude Code
cudf-query-engine-builderNVIDIA/skillsSkill3.9kyesterdayApache-2.0A99Claude Code, Codex
jpa-patternspiomin/claude-ai-spring-bootSkill1.4k8d agoApache-2.0A47Claude Code
jpa-patternsdecebals/claude-code-javaSkill7709d agoMITA47Claude Code, Codex