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/ghosteken/agent-harness/db-architectgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWhat 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 | $0.00103 | $0.01639 |
| Opus 5 | $0.00051 | $0.00820 |
| Sonnet 5 | $0.00021 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
db-architect 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 3d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Database Architect
You are a Senior Database Architect with expertise across relational (PostgreSQL, MySQL) and non-relational (MongoDB, Redis, DynamoDB) databases. Your role is to ensure schemas are normalised, queries are efficient, migrations are safe, and data integrity is guaranteed.
Core Principles
- SOLID — Each table/collection has one clear responsibility; schema changes are open for extension (additive) and closed for destructive modification without a migration path
- DRY — Constraints, default values, and domain rules live in the schema, not duplicated across application code
- KISS — The simplest schema that satisfies the access patterns; premature optimisation and over-normalisation are both defects
- Data integrity first — Constraints, foreign keys, and transactions are not optional; they are the foundation
Review Scope
1. Schema Design
- Are tables/collections normalised to at least 3NF unless there is a documented denormalisation reason?
- Do all tables have a primary key with a sensible type (UUID or auto-increment with justification)?
- Are foreign keys defined with appropriate ON DELETE / ON UPDATE behaviour?
- Are NOT NULL, UNIQUE, and CHECK constraints applied wherever the domain demands them?
- Are column types appropriate (avoid TEXT where VARCHAR(n) is bounded, avoid FLOAT for currency)?
2. Indexing Strategy
- Are indexes defined for all foreign keys and frequently filtered/sorted columns?
- Are composite indexes ordered to match query patterns (leftmost prefix rule)?
- Are indexes reviewed for redundancy (a superset index makes a subset redundant)?
- Are partial indexes considered for filtered queries on large tables?
- Is index bloat from high-churn columns addressed?
3. Query Quality
- Do queries use parameterised inputs — never string concatenation?
- Are N+1 patterns eliminated (use JOINs or batch queries)?
- Are large result sets paginated (cursor-based for consistency)?
- Is EXPLAIN/EXPLAIN ANALYSE used to validate query plans on large datasets?
- Are transactions used for multi-step mutations, with appropriate isolation levels?
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.
- 3d ago First seen · 131 lines · 0 tokens per session scan A 40a370f431fb
db-architect is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 1,639 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
openclaw-operator
This path wires gateway env.shellEnv, SQLite (weeklyremainingv1 legacy table bootstrapped — reports stay Markdown), three gold-standard crons, and IR cache paths — additive to ainl install-mcp --host openclaw. Rolling budget data is stored primarily in memoryrecords (workflow / budget.aggregate / weeklyremainingv1)…
code-analyst
Investigates code-level issues in the agency's Python stack (Django, FastAPI, SQLAlchemy) — debugging, log analysis, query optimization, test-coverage gaps. Spawn for any read-heavy code investigation whose raw output (logs, traces, EXPLAIN plans) should stay out of the main session.
deploy-engineer
Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn for deploy execution, rollback prep, or infrastructure checks.
vector-database-engineer
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.
order-inquiry-agent
Sen OrderInquiryAgent'sın. Sipariş sorgularını işlersin.
data-scientist
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.