rock-db

rock-db is a skill for Claude Code from Triumph-Tech/rock-claude-plugins. It costs 193 tokens per session (6,419 once invoked), scanned A, original, Apache-2.0.

A helper for writing SQL Server queries for Rock RMS databases, a church-management system, and for exploring Rock's tables, relationships, types, indexes, and enumerated values.

In plain words
What is it for?
Use it to write SELECT and data-change queries, inspect the Rock data model, trace foreign-key paths, and get indexing guidance.
Why use it?
It helps produce safer and more efficient database queries without guessing identifiers or making assumptions about a specific Rock environment.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the rock-techkit plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/triumph-tech/rock-claude-plugins/rock-db
Any agent
npx skills add Triumph-Tech/rock-claude-plugins --skill rock-db
Clone the repo
git clone --depth 1 https://github.com/Triumph-Tech/rock-claude-plugins

Made for: Claude Code.

Or install rock-techkit, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for rock-db

README.md
[![agentmods](https://agentmods.dev/badge/skills/triumph-tech/rock-claude-plugins/rock-db.svg)](https://agentmods.dev/skills/triumph-tech/rock-claude-plugins/rock-db)
Your own site
<a href="https://agentmods.dev/skills/triumph-tech/rock-claude-plugins/rock-db"><img src="https://agentmods.dev/badge/skills/triumph-tech/rock-claude-plugins/rock-db.svg" alt="Measured on agentmods" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00193 $0.06419
Opus 5 $0.00097 $0.03209
Sonnet 5 $0.00039 $0.01284
Haiku 4.5 $0.00019 $0.00642

Measured 5d ago against content hash 8f0304a25924, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

rock-db 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 5d 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.

rock-techkit/skills/rock-db/SKILL.md · 609 lines

How it starts

The opening of the file, as written. The whole thing — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Magnus Rock DB Helper

Magnus Rock DB Helper helps write correct, performant T-SQL queries against Rock RMS databases, and answers questions about Rock's data model. It covers SELECT queries, full CRUD operations, performance and indexing guidance, and schema exploration.

Audience: The Rock RMS community broadly. Do not bake in environment-specific assumptions. Use safe patterns (e.g., join to DefinedValue by GUID rather than hardcoding Ids).

Not in scope: Lava SQL snippets.


Workflow

REQUIRED: Do not generate any SQL or read any schema files until step 1 is complete. Do not assume or default to any version -- you MUST call AskUserQuestion and wait for the response.

Do not show a plan or ask for approval before writing the query. Write it directly.

CRITICAL: Never guess, invent, or fabricate GUIDs or integer Id values. Ever. If a GUID or Id is needed and is not present in the schema files, samples, or field notes, use a descriptive token in curly braces (e.g. {family-group-type-guid}) and include a helper SQL comment below the query so the user can look it up themselves. A wrong GUID silently returns bad data. There are no acceptable exceptions to this rule.

Example of correct behavior when a GUID is unknown:

WHERE gt.[Guid] = '{family-group-type-guid}'

/*
  I'm not able to provide the proper GroupType GUID -- use the SQL below to look up the correct value.
  SELECT gt.[Name], gt.[Guid] FROM [GroupType] gt WHERE gt.[Name] LIKE '%YourGroupType%'
*/
  1. Identify the Rock version. If the user hasn't stated it and no version has been set this session, call the AskUserQuestion tool immediately -- before any other action:

    question: "Which Rock version are you on?"
    options: [v17, v18, v19]
    

    Do not proceed until the user responds. Do not guess, infer, or default to the latest version. Once selected, treat it as the session default -- do not ask again unless the user explicitly requests a change.

  2. Read the schema index. Navigate to schemas/vNN/INDEX.md for the version the user specified.

  3. Check the Concept to Table Mapping (below) if the user's request uses church or ministry terminology rather than Rock table names. Identify the relevant tables before reading schema files.

  4. Read individual table files as needed from schemas/vNN/<domain>/<Table>.md.

  5. Check system GUID files if the query involves DefinedType values or GroupType roles by name. Read schemas/vNN/SYSTEM-GUIDS-DEFINEDTYPES.md for DefinedType and DefinedValue GUIDs, and schemas/vNN/SYSTEM-GUIDS-GROUPTYPES.md for GroupType and role GUIDs. See Schema Navigation below for how to use these files and what to do when a GUID is not found.

  6. Check samples/INDEX.md for a relevant query that can serve as a starting point or reference.

  7. Generate the SQL following the style and output format rules below.

Read the full file on GitHub · 609 lines

Files

What ships with it

60 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.

Changes

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.

  1. 5d ago First seen · 609 lines · 193 tokens per session scan A 8f0304a25924

Subscribe to this mod's changes

rock-db is a skill published in the GitHub repository Triumph-Tech/rock-claude-plugins (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 193 tokens to every session and 6,419 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

sdk-design

Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…

gridaco/grida · 199 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

supabase

Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…

PentesterFlow/agent · 120 tokens

nornicdb-cypher-queries

Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.

orneryd/NornicDB · 79 tokens

dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…

awslabs/agent-plugins · 229 tokens