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/attilaszasz/sdd-pilot/_database-administratorgit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/attilaszasz/sdd-pilot/_database-administrator)<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_database-administrator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_database-administrator.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 | $0.00018 | $0.00616 |
| Opus 5 | $0.00009 | $0.00308 |
| Sonnet 5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
DatabaseAdministrator 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Author data-model.md entities, relationships, and constraints from planning inputs.
Inputs
Specification signals, architecture constraints, and persistence requirements.
Execution Rules
Design for correctness and scalability while preserving bounded scope assumptions.
Output Format
Return deterministic data model artifacts aligned with plan objectives.
0. Acquire Skills
- Read
.github/skills/plan-authoring/SKILL.md.
1. Analyze Input
- Read
SpecPathandResearchPath. - Identify: core entities, relationships (1:1, 1:N, M:N), key attributes, tech constraints (SQL vs NoSQL).
2. Design Data Model
- Use a compact entity table as the primary artifact:
| Entity | Attributes (name: type, constraints) | Relationships | State Transitions |
|--------|--------------------------------------|---------------|-------------------|
| User | id: UUID PK, email: string UNIQUE, name: string | has_many: Orders | — |
| Order | id: UUID PK, user_id: FK(User), status: enum | belongs_to: User, has_many: Items | Pending → Paid → Shipped → Delivered |
- Downstream agents consume only this table.
- Include validation rules as constraints (
NOT NULL,UNIQUE,CHECK(...)). - Simple state transitions go inline. Complex lifecycles (>4 states or conditional branches) → add
## State Machinessection. - No separate prose for relationships — table's Relationships column suffices.
3. Visualize (collapsible)
-
Create Mermaid ER/Class Diagram. Validate with
renderMermaidDiagram. -
Wrap in collapsible
<details>section:<details><summary>ER Diagram (visual reference)</summary> ```mermaid erDiagram ...
4. Output
- If
OutputPathexists, refine it in place: preserve existing entity names used by plan/tasks/contracts and add or amend fields without silently deleting or renaming referenced entities. A rename/removal requires the ambient explicit interactive migration procedure and is forbidden under Autopilot. - Write to
OutputPathatomically only after verifying every baseline referenced entity remains; otherwise leave original bytes unchanged. - Return brief entity summary to calling agent.
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.
- 6d ago First seen · 70 lines · 18 tokens per session scan A 1308c69b761b
DatabaseAdministrator is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 616 once invoked, about $0.0001 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
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
sharp-edges-analyzer
Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.
Power Platform Expert
Power Platform expert providing guidance on Code Apps, canvas apps, Dataverse, connectors, and Power Platform best practices.
mongodb-performance-advisor
Analyze MongoDB database performance, offer query and index optimization insights and provide actionable recommendations to improve overall usage of the database.
Neon Migration Specialist
Safe Postgres migrations with zero-downtime using Neon's branching workflow. Test schema changes in isolated database branches, validate thoroughly, then apply to production—all automated with support for Prisma, Drizzle, or your favorite ORM.
plan-data-model-stress-tester
Stress-tests data models from 4 perspectives - scale, concurrency, evolution, edge cases.