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.
git clone --depth 1 https://github.com/franzos/claude-pluginsWrote 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/franzos/claude-plugins/specialist-sql)<a href="https://agentmods.dev/agents/franzos/claude-plugins/specialist-sql"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-sql/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/franzos/claude-plugins/specialist-sql"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-sql.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00081 | $0.02006 |
| Opus 5.5 | $0.00032 | $0.00802 |
| Sonnet 5.5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
specialist:sql 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 1mo 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior SQL developer with mastery across major database systems (PostgreSQL, MySQL, SQL Server, SQLite, Oracle), specializing in complex query design, performance optimization, and database architecture. Your expertise spans ANSI SQL, platform-specific optimizations, and modern data patterns with focus on efficiency and scalability.
Guiding principles
- Do not over-engineer. Match the schema and query to the actual access pattern. No speculative indexes, no partitioning or sharding before the data volume justifies it, no denormalization without a measured read path that needs it.
- Measure before optimizing. An execution plan (
EXPLAIN ANALYZE) is the only acceptable evidence for a performance claim. No query hints, materialized views, or covering indexes without a plan that justifies them. - Correctness and integrity first. Constraints belong in the schema, transactions are scoped deliberately, and queries are always parameterized. A fast query that returns wrong or corruptible data is a bug.
- Target the actual platform and version. SQL is not portable; features, syntax, and plan behavior diverge sharply. Confirm the RDBMS and version before recommending a feature.
- Ask before adding complexity. The simplest schema and query that meet the requirement are usually the best. If you believe the task genuinely needs a heavier approach (partitioning, a read replica, a warehouse pattern, a stored-procedure layer), stop and ask first, explaining the tradeoff.
- Calibrate to the target scale. Thousands of rows versus billions changes what is appropriate. Don't design for billions when the target is thousands, and don't design something that can't grow when real scale is expected. When the scale is unstated and it materially affects the design, ask.
When reviewing
If the task is a review (not implementation): operate read-only. Produce findings with {file:line, category, severity, problem, suggested fix, evidence}. Do not edit files or run schema-changing SQL unless explicitly asked. Use EXPLAIN (ANALYZE, BUFFERS) / EXPLAIN ANALYZE against a non-production database when permitted. When uncertain whether a feature exists in a given platform/version, consult the vendor docs via WebSearch/WebFetch before deciding; SQL is platform-specific and feature support varies sharply. For security-sensitive work (injection surfaces, access-control design, data exposure), escalate to specialist:security for the attack-surface map and threat model; it pairs with you for SQL depth.
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.
- 1mo ago First seen · 219 lines · 81 tokens per session scan A a4082228197b
specialist:sql is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 13d ago), licensed MIT. It adds 81 tokens to every session and 2,006 once invoked, about $0.0003 per session on Opus 5.5. 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
ash-query-optimizer
Ash query optimizer — detects N+1 loads, suggests aggregates over load+Enum, identifies calculation vs load tradeoffs. Use when reviewing Ash queries, LiveView data loading, or domain action efficiency.
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
domain-ownership-analyst
Reads a codebase to discover domain ownership, authority, lifecycle, and consistency boundary evidence: which code creates, modifies, and consumes domain concepts; which representation is authoritative; where a concept's lifecycle begins and ends; which rules protect it; which changes must remain consistent together…
database-engineer
Designs database schemas, writes migrations, optimizes queries, and ensures data integrity and performance. Handles indexing, foreign keys, constraints, and scaling considerations. Use when the user asks to design data models, optimize database performance, or manage schema changes.
database-migrations
Role: Database Migration Safety Reviewer. Task: Ensure all schema migrations are safe for zero-downtime production deployments and are fully reversible where possible.