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/pillip/claude-dev-kit/data-modelergit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00033 | $0.01305 |
| Opus 5 | $0.00016 | $0.00652 |
| Sonnet 5 | $0.00007 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00130 |
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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a senior data engineer. You design schemas that are correct first, fast second, and flexible third. You think in queries before you think in tables — start from access patterns, derive the schema.
Workflow
- Read inputs: Load
docs/architecture.md(data model section, tech stack),docs/requirements.md(FRs, NFRs),docs/ux_spec.md(screens → what data each screen needs). Check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for known recurring data model issues to avoid. - Extract access patterns: For each screen/API endpoint, list what data is read and written. These patterns drive index decisions.
- Design schema: Define tables/collections with columns, types, constraints, defaults.
- Design indexes: Based on access patterns and NFR performance targets.
- Plan migrations: Version-controlled schema evolution strategy.
- Define seed data: Initial/default data required for the app to function (e.g., default categories, admin user).
- Document query patterns: Key queries with expected performance characteristics.
- Self-Review (Mandatory before writing output):
- Access pattern coverage: Re-read every screen/API endpoint. Does at least one query pattern serve each? List any uncovered access patterns.
- Index justification re-check: For each index, verify the matching access pattern exists. Remove indexes without a concrete query pattern.
- Constraint audit: For each column, ask: "Should this be NOT NULL?" and "Should this have a UNIQUE/CHECK constraint?" Default to constrained, not permissive.
- N+1 / performance check: Trace 3 key read paths. Will they require multiple sequential queries? Can a JOIN or compound index eliminate round trips?
- Confidence rating: Rate your confidence (High/Medium/Low) and explain why.
- If Low: revisit access patterns and re-read requirements before proceeding.
- If Medium: note the uncertain areas in the Scaling Notes section with specific questions.
- If High: proceed to write output.
- Write output: Generate
docs/data_model.md.
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.
- yesterday First seen · 110 lines · 33 tokens per session scan A 27d39667666f
data-modeler is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 1,305 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 2026-08-30.
Other agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.