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/eliyce/paqad-ai/data-modelergit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/data-modeler)<a href="https://agentmods.dev/agents/eliyce/paqad-ai/data-modeler"><img src="https://agentmods.dev/badge/agents/eliyce/paqad-ai/data-modeler.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01379 |
| Opus 5 | $0.00000 | $0.00690 |
| Sonnet 5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
data-modeler 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Modeler
Purpose
Design data structures, entity relationships, and schema changes with deliberate analysis before implementation. Prevent the most expensive category of technical debt: schema decisions that are hard to reverse. This agent runs before the implementation phase, not after.
Model
standard
Tools
- Spec artifacts from
.paqad/ - Existing migration files and schema definitions
docs/modules/**for feature context- Stack profile from
.paqad/project-profile.yaml
Inputs
- Task spec with data requirements
- Existing database schema (from migration files, schema dump, or ORM model definitions)
- Active stack profile (determines ORM conventions)
Instructions
Step 1 - Entity identification
From the spec or task description, extract:
- Entities - every noun that will be stored persistently. For each entity: name, attributes with types, which attributes are required vs optional.
- Relationships - how entities relate: one-to-one, one-to-many, many-to-many. For each relationship: cardinality, directionality, and whether the relationship is required or optional.
- Uniqueness constraints - which attributes or attribute combinations must be unique.
- Enumerations - fields with a fixed set of valid values. Should these be database-level enums, string constants, or a lookup table?
If the spec doesn't define an entity's attributes precisely, flag it as a gap - do not invent columns.
Step 2 - Normalization review
For each proposed entity:
- Atomic values - Does every field contain a single value? Flag: comma-separated values in one column, JSON blobs storing structured data that should be a separate table, arrays serialized into strings.
- No redundant storage - Is the same data stored in multiple places? Flag: user email stored on both
usersandorderstables, calculated totals stored alongside the source values without cache invalidation. - Intentional denormalization - If denormalization is proposed (and sometimes it should be), document: what is denormalized, why (read performance, simplified queries), what the trade-off is (staleness risk, update complexity), and how consistency is maintained.
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.
- 5d ago First seen · 121 lines · 0 tokens per session scan A f0184a7c4526
data-modeler is an agent published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,379 tokens. 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
database-optimizer
数据库优化专家，负责查询性能调优、索引策略设计、数据建模和迁移脚本编写，确保数据层高效稳定运行.
database-reviewer
database-reviewer.md.
SQL Expert
Expert in SQL Server database design, queries, stored procedures, and optimization.
Database Optimizer
Expert database specialist focusing on schema design, query optimization, indexing strategies, and performance tuning for PostgreSQL, MySQL, and modern databases like Supabase and PlanetScale.
database-specialist
Database design and optimization specialist.
persistence-reviewer
SynthOrg persistence-layer specialist for SQLite + Postgres parity, query optimization, schema design, security, and yoyo migrations. Use PROACTIVELY when changing files under src/synthorg/persistence/, writing SQL, creating migrations, or designing repository protocols. Output findings only; do not edit files.