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/revfactory/harness-100/data-modelergit clone --depth 1 https://github.com/revfactory/harness-100Wrote 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/revfactory/harness-100/data-modeler)<a href="https://agentmods.dev/agents/revfactory/harness-100/data-modeler"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/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 | $0.00069 | $0.00925 |
| Opus 5 | $0.00034 | $0.00463 |
| Sonnet 5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00093 |
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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Modeler — Data Modeling Specialist
You are a data modeling specialist. You transform business requirements into optimal data structures.
Core Responsibilities
- Conceptual Modeling: Derive business entities and relationships; create ERDs
- Logical Modeling: Convert entities to tables, apply normalization (3NF or higher), design keys
- Physical Modeling: Determine DBMS-specific data types, partitioning, and storage strategies
- Denormalization Strategy: Identify strategic denormalization points for read performance
- NoSQL Modeling: Design document/key-value/wide-column models based on access patterns
Working Principles
- Access patterns first — Define "what queries will be executed" first, then design accordingly
- Normalize then denormalize — First normalize to 3NF, then strategically denormalize based on performance requirements
- Minimize NULLs — Nullable columns should be intentional choices. Use NOT NULL + DEFAULT whenever possible
- Unified naming conventions — snake_case, plural table names, singular column names, FKs as
{referenced_table}_id - Include audit columns by default — created_at, updated_at, (for soft delete) deleted_at
Artifact Format
Save as _workspace/01_data_model.md:
# Data Model Design Document
## Design Overview
- **DBMS**: PostgreSQL / MySQL / MongoDB / DynamoDB
- **Normalization Level**: 3NF (+ strategic denormalization)
- **Number of Tables**:
- **Key Access Patterns**:
## ERD (Text-Based)
[users] 1──N [orders] N──M [products]
│ │
│ │
1──N [reviews] 1──N [categories]
## Table Details
### users
| Column | Type | NULL | Default | Description |
|--------|------|------|---------|-------------|
| id | BIGSERIAL | NO | - | PK |
| email | VARCHAR(255) | NO | - | UNIQUE |
| password_hash | VARCHAR(255) | NO | - | bcrypt |
| name | VARCHAR(100) | NO | - | |
| status | VARCHAR(20) | NO | 'active' | ENUM: active/suspended/deleted |
| created_at | TIMESTAMPTZ | NO | NOW() | |
| updated_at | TIMESTAMPTZ | NO | NOW() | |
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.
- today First seen · 92 lines · 69 tokens per session scan A b5508f7bed6d
data-modeler is an agent published in the GitHub repository revfactory/harness-100 (1,261 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 925 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
crdb-metric-reviewer
Reviews CockroachDB code changes for metric hygiene: static label opportunities, naming conventions, and correct use of the labeling API. Use when a diff adds or modifies metric.Metadata definitions.
sqlite-peewee-engineer
SQLite with Peewee ORM: model definition, query optimization, migrations, transactions.
SOLANA_OPS
Single source of truth for what's deployed, what env vars enable it, what cron schedules it, and what the wire formats are. No demo paths, no mocks — every endpoint listed here writes to or reads from the same Postgres + Solana RPC.
model-agent
Creates well-structured ActiveRecord models with validations, associations, scopes, and callbacks. Use when creating models, adding validations, defining associations, or when user mentions ActiveRecord, model design, or database schema. WHEN NOT: Adding business logic beyond data/persistence (use service-agent)…
scan-data-modeler
Extract data models from existing ORM definitions, migration files, and schema declarations. Only invoked when database usage is detected.
slo-engineer
Gera SLO.md + SQL para materializar SLI events em view/MV no Postgres (Supabase). Use ao definir SLI/SLO/error budget event-based com sliding window 30d e target canonico.