DYLA-ai: Skill for Claude Code

.agents/skills/data-model/SKILL.md

data-model is a skill for Claude Code from Federico-Anastasi/DYLA-ai. It costs 36 tokens per session (2,216 once invoked), scanned A, original, MIT.

A conversational planning guide that turns a project brief into a checked data model: the tables, connections between them, and outside-system integrations an application needs. It saves the result in datamodel.json and updates context.md.

In plain words
What is it for?
Use it when starting a project or revisiting its information structure. It helps define records such as users or orders, their relationships, and connections to other services.
Why use it?
It helps settle how information is stored and related before implementation begins. The short question-and-answer process exposes missing requirements and validates the proposed structure.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Federico-Anastasi/DYLA-ai's own configuration. It tells Claude Code how to work on DYLA-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DYLA-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Federico-Anastasi/DYLA-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Federico-Anastasi/DYLA-ai/main/.agents/skills/data-model/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Federico-Anastasi/DYLA-ai

Made for: Claude Code.

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 data-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/data-model/github.svg)](https://agentmods.dev/skills/federico-anastasi/dyla-ai/data-model)
Your own site
<a href="https://agentmods.dev/skills/federico-anastasi/dyla-ai/data-model"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/data-model/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 data-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/federico-anastasi/dyla-ai/data-model"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/data-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,216 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 $0.00036 $0.02216
Opus 5 $0.00018 $0.01108
Sonnet 5 $0.00007 $0.00443
Haiku 4.5 $0.00004 $0.00222

Measured 12d ago against content hash 175381e5730a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

data-model 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.

.agents/skills/data-model/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/data-model — Data model

Reads the project brief and produces the validated data model.

UX: chat stays conversational. The deliverable is never presented as a markdown table in chat — the user reads the table and the diagram in the viewer next to the chat, from data_model.json. In chat you discuss it in words, citing elements by id (e.g. the refund_request table). The user does not have to type ids: every element in the viewer has a chat icon that sends you a ready-made [REFERENCE] — point them at that button when it is unclear what they mean. When you cite a chapter of the brief, write [[brief:Chapter title]]: it renders as a clickable reference that opens the document at that point.


PROTOCOL

  1. Read context.md — where is the project? (Q&A already done? Data model already there?)
  2. Read the brief — find the brief file in the project folder
  3. If data_model.json already exists: ask "The data model already exists. Regenerate it from scratch, or edit it?"
  4. If context.md has no Q&A: run the Q&A (BLOCKING — 5 to 7 questions, no more)
  5. Write data_model.json straight away with meta.status: "draft"
  6. Present a conversational summary (BLOCKING — wait for validation or edits)
  7. On confirmation: set meta.status: "confirmed"
  8. Update context.md
  9. Check consistency with the deliverables that already exist

Note: data_model.drawio and data_model.html are exports, generated on demand by the backend from data_model.json (GET /api/projects/{project}/export/data_model.drawio and .../data_model.html). This skill does not produce them.


PHASE 1 — READING

Read ALL of these before you go on:

  • the brief: projects/{project}/brief.json, or the input document (brief.md, or its extracted text under .extracted/ if it is a PDF or a Word file)
  • projects/{project}/meetings/* — if the project source is discovery: the real requirements are in the transcripts before they are in the brief
  • projects/{project}/docs/* — client documents (md, pdf, docx, xlsx, images; binaries have their text extracted under .extracted/)
  • projects/{project}/context.md
  • projects/{project}/data_model.json — if it exists
  • projects/{project}/estimate.json — if it exists
  • knowledge/ — if the folder exists: naming conventions, house patterns, client specifics. Nothing there is assumed: if a convention matters and the folder is silent about it, ask the user rather than inventing one

Read the full file on GitHub · 199 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. 12d ago First seen · 199 lines · 36 tokens per session scan A 175381e5730a

Subscribe to this mod's changes

data-model is a skill published in the GitHub repository Federico-Anastasi/DYLA-ai (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,216 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.