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 skills/runxhq/runx/sql-analystnpx skills add runxhq/runx --skill sql-analystgit clone --depth 1 https://github.com/runxhq/runxWrote 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/skills/runxhq/runx/sql-analyst)<a href="https://agentmods.dev/skills/runxhq/runx/sql-analyst"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sql-analyst.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 | $0.00032 | $0.00652 |
| Opus 5 | $0.00016 | $0.00326 |
| Sonnet 5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
sql-analyst 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Analyst
Use this skill to answer a bounded data question from one declared, typed data
source operation. The default validates the plan, performs the exact
data-store read, and interprets only that returned evidence. The explicit
plan runner stops at a reviewable read-only plan.
The schema and optional sample snapshot must carry stable upstream SHA-256 digests and observation times. Runx treats them as caller-supplied provenance, not provider verification. Deterministic admission rejects stale or malformed sources, write intent, invalid identifiers or dialects, unknown allowed tables, and unbounded row requests before the model runs. The model designs a plan against a normalized table/field index. A deterministic finalizer then rejects invented tables and fields, untyped joins, unstructured filters, literal filter values, invalid limits, incomplete interpretation, and write tokens.
This skill never emits or executes raw SQL. The default requires a validated
execution_context for data-store.read_projection, read_events, or
list_stream_heads; it performs that read and returns an interpretation. The
explicit plan runner may omit the context and returns planned_only.
Composes
data-store#list_stream_headsdata-store#read_eventsdata-store#read_projection
Inputs
question: bounded analysis question.schema_summary: source-bound available tables and fields.dialect:postgres,sqlite, ormysql.as_ofandmax_schema_age_days: deterministic source-freshness boundary.sample_rows: optional source-bound snapshot containing at most 20 non-sensitive rows.constraints: allowed tables, maximum rows, and privacy limits.execution_context: required for the default; an exact governed data-store read runner and bounded resource inputs. It is optional only forplan.
Output
The default returns analysis_result from the validated plan and actual
runx.data.operation_result.v1 evidence. plan returns the existing
runx.data.sql_analysis_plan.v1 packet.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 70 lines · 32 tokens per session scan A c8807a325e10
sql-analyst is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 652 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 skills, from other repositories
Database Management
Explore schema, run queries, and manage migrations via the systemprompt CLI.
manage_services
Operate the running Enterprise Demo stack: services, the Postgres database, and scheduled jobs.
schema
Designing database schemas, migrations, and multi-tenant architecture: RLS, tenant routing, provisioning, quotas, and isolation. Not for query-plan tuning (Tuner).
seek
Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.
shard
Designing multi-tenant architectures with tenant isolation strategies, RLS, routing, and scale design for SaaS. Use when designing multi-tenant SaaS systems or tenant isolation.
tuner
Tuning database queries via EXPLAIN ANALYZE, query plan optimization, index recommendations, and slow query detection. Not for schema/migrations (Schema) or non-DB performance (Bolt).