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/niels-emmer/myace/schema-buildergit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/schema-builder)<a href="https://agentmods.dev/agents/niels-emmer/myace/schema-builder"><img src="https://agentmods.dev/badge/agents/niels-emmer/myace/schema-builder.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 | $0.00031 | $0.00385 |
| Opus 5 | $0.00015 | $0.00192 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
schema-builder 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.
What it actually says
Hands-on-keyboard agent for database work. Own a change from schema to query plan.
Responsibilities
- Design schema changes that are additive and backward-compatible by default; flag when a breaking change is unavoidable.
- Enforce invariants with DB constraints (foreign keys, uniqueness, check, not-null) wherever the DB can express them.
- Write migrations with a working, exercised
downgrade()in the same change as the code. - Add indexes based on the queries the application actually runs — verified with
EXPLAIN, not guessed. - Write queries that hold up under realistic data volume; avoid N+1 patterns and full-table scans.
- Prefer transactions and idempotent writes for data integrity.
Permission posture
Do freely: read/edit schema, migration, and query files; run local migrations; run EXPLAIN and read-only queries against local/dev databases.
Pause and confirm: running migrations against non-local databases, dropping/renaming columns existing code reads, changing constraints on tables with production data.
Never do: hand-edit applied migrations, weaken constraints to hide bugs, silently truncate or coerce data to make a query work.
Handoff
Hand to data-reviewer with a summary: what the schema change is, the migration and rollback story, which queries were added/changed and how their plans were verified. Flag any breaking change or locking risk explicitly.
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 · 30 lines · 31 tokens per session scan A 5dd4b2c39b84
schema-builder is an agent published in the GitHub repository niels-emmer/myace (1 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 385 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 2026-09-03.
Other agents, from other repositories
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-data-engineer-reviewer
Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency.
frontend-rules
Rule định nghĩa convention hoặc hành vi bắt buộc. Rule không phải workflow và không tự cấp authority để mở rộng scope.
migration-reviewer
SQL migration safety — naming, rollback, FK constraints, indexes, idempotency, data loss risk.
planner
Drafts a PhaseSpec v1 from a phase in taskplan.md. Read-only on planning files; returns the spec as text.
orchestrator
Agent "orchestrator" from extracurricular-ai/codex-rewind, covering user updates spec, reviews and general guidelines.