agentmods.dev

dsql

dsql is a skill for Claude Code from awslabs/mcp. It costs 43 tokens per session (321 once invoked), scanned A, a copy of amazon aurora dsql, Apache-2.0.

A guide for building applications with Amazon Aurora DSQL, a serverless distributed SQL database compatible with PostgreSQL. It covers database structure, queries, migrations, authentication, and multi-tenant designs.

In plain words
What is it for?
Use it to create or change schemas, run queries, migrate data, inspect query plans, load data, and design tenant isolation.
Why use it?
It reduces mistakes when working with DSQL’s constraints, connection rules, data formats, and application-level relationships.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex.

not rated 9.7k +17 changed 3d ago A scan 43 tokens copy · 100% Apache-2.0
View the source file awslabs/mcp awslabs.github.io
About the project

AWS MCP Servers is a collection of Model Context Protocol servers that let AI agents access AWS documentation and services through standardized tools. It is for developers building coding agents or other software that works with AWS. The catalogue includes MCP servers and related add-ons for using AWS through agents.

awslabs/mcp · 9,661 stars · on GitHub · awslabs.github.io

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/awslabs/mcp/dsql-skill
Any agent
npx skills add awslabs/mcp --skill dsql-skill
Clone the repo
git clone --depth 1 https://github.com/awslabs/mcp

Made for: Claude Code.

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 dsql

README.md
[![agentmods](https://agentmods.dev/badge/skills/awslabs/mcp/dsql-skill.svg)](https://agentmods.dev/skills/awslabs/mcp/dsql-skill)
Your own site
<a href="https://agentmods.dev/skills/awslabs/mcp/dsql-skill"><img src="https://agentmods.dev/badge/skills/awslabs/mcp/dsql-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00043 $0.00321
Opus 5 $0.00022 $0.00161
Sonnet 5 $0.00009 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 3d ago against content hash 26c45696df34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dsql 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.

The scan reads SKILL.md. This mod also ships 7 executable files (mcp/tools/safe_query.py, scripts/cluster-info.sh, scripts/create-cluster.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to amazon aurora dsql — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/aurora-dsql-mcp-server/skills/dsql-skill/SKILL.md · 38 lines

What it actually says

Aurora DSQL Skill Moved

This standalone skill is deprecated. The canonical DSQL skill is now:

plugins/databases-on-aws/skills/dsql/SKILL.md in awslabs/agent-plugins.

Redirect

  1. Check whether the canonical dsql skill is already available.
  2. If it is available, read and follow its SKILL.md, then read only the references that canonical skill routes to.
  3. Do not combine canonical guidance with content from this deprecated standalone skill.
  4. If the canonical skill is unavailable, explain that the DSQL skill moved to awslabs/agent-plugins.
  5. Get explicit user approval before installing anything or changing user configuration.

Repository-reading tools may read the canonical skill to provide advisory guidance. Reading its repository does not install the plugin, hooks, scripts, or MCP servers.

For Claude Code, the verified installation commands are:

/plugin marketplace add awslabs/agent-plugins
/plugin install databases-on-aws@agent-plugins-for-aws

For Codex and Cursor, use the current canonical installation instructions.

Files

What ships with it

59 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. 3d ago Changed · -304 lines · -153 tokens per session 26c45696df34
  2. 6d ago First seen · 342 lines · 196 tokens per session scan A 6bdc4d21206d

Subscribe to this mod's changes

dsql is a skill published in the GitHub repository awslabs/mcp (9,661 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 321 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to amazon aurora dsql, differing in 2 lines, and is treated as a copy.

Databasesawsmcpmcp-clientmcp-clientsmcp-hostmcp-server
Related

Other skills, from other repositories

release-checklist

Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application boot time, then produces a pass/warn/fail report with a concrete remediation plan. Invoked with /release-checklist [git-ref-range]. Built to…

maximhq/bifrost · 82 tokens

odoo-mcp-efficient-queries

Paginate, scope fields, and count-before-fetch when working with Odoo models that hold lots of data (mail.message, stock.move.line, account.move.line, sale.order.line, ir.attachment, res.partner across multi-company). Use when building a report, syncing data, iterating through all records of a model, or when a query…

AlanOgic/mcp-odoo-adv · 121 tokens

odoo-mcp-relationships

Read and write relational fields in Odoo — many2one (single link), one2many (list of child records), many2many (tag-style set). Use when creating a sale.order with order lines, tagging a partner with multiple categories, adding/removing followers, replacing a set of attributes, or when writes to relational fields fail…

AlanOgic/mcp-odoo-adv · 136 tokens

investigate-issue

Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when asked to investigate, analyze, triage, or plan work for a GitHub issue. Invoked with /investigate-issue or /investigate-issue (prompts for ID).

maximhq/bifrost · 78 tokens

resolve-pr-comments-stack

Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…

maximhq/bifrost · 99 tokens

split-commit-into-stack

Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…

maximhq/bifrost · 96 tokens