Atlas is a language-independent tool that treats a database schema as code and manages changes to it through declarative or versioned migrations. Developers use it to describe, compare, plan, lint, and apply database schemas expressed in SQL, HCL, or an ORM. The catalogue entries provide add-ons for operating Atlas workflows.
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 skills add ariga/atlas --skill atlas-lakebasegit clone --depth 1 https://github.com/ariga/atlasWrote 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/ariga/atlas/atlas-lakebase)<a href="https://agentmods.dev/skills/ariga/atlas/atlas-lakebase"><img src="https://agentmods.dev/badge/skills/ariga/atlas/atlas-lakebase/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/skills/ariga/atlas/atlas-lakebase"><img src="https://agentmods.dev/badge/skills/ariga/atlas/atlas-lakebase.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 | $0.00140 | $0.02491 |
| Opus 5.5 | $0.00056 | $0.00996 |
| Sonnet 5.5 | $0.00028 | $0.00498 |
| Haiku 4.5 | $0.00014 | $0.00249 |
Grade A, and why
atlas-lakebase 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 today.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlas for Databricks Lakebase
What is specific to Databricks Lakebase when Atlas manages the schema. Lakebase is managed PostgreSQL,
and Atlas connects to it with the postgres driver: the atlas-postgres skill covers the schema work
(URL scope, the dev database, roles and grants, objects, lint, and tests), and the atlas skill covers
the workflows. This skill covers connecting to Lakebase and the objects Lakebase manages. Guide:
https://atlasgo.io/guides/postgres/databricks-lakebase.
Requires
The atlas and atlas-postgres skills, installed next to this one. Read ../atlas-postgres/SKILL.md
and ../atlas/SKILL.md before you start, and follow them for everything this skill does not cover:
this skill only adds what differs on Lakebase. If one is missing, download
https://atlasgo.io/skills//SKILL.md to ../<skill>/SKILL.md, and each reference file listed in
its Files section to ../<skill>/references/<name>.
Rules
-
Check the login first with
atlas whoami. If it shows no login, ask the user to runatlas login: thedatabricks_lakebase_tokendata source needs it. A user without an account can start a free trial withatlas login. An Atlas release older than the data source fails every env in the file withmissing data source handler for "databricks_lakebase_token": runatlas version, and install the latest release. -
Connect with a token from the data source.
endpointis the endpoint path, and the URL user is the Postgres role of the identity the token is issued to: the email of a Databricks user, or the application ID of a service principal.urluserinfosets both and escapes the@:locals { host = "ep-example.database.us-west-2.cloud.databricks.com" user = "[email protected]" } data "databricks_lakebase_token" "db" { endpoint = "projects/my-app/branches/production/endpoints/primary" } env "lakebase" { url = urluserinfo( "postgres://${local.host}:5432/databricks_postgres?sslmode=require&search_path=public", local.user, data.databricks_lakebase_token.db, ) dev = "docker://postgres/17/dev?search_path=public" // Functions that Lakebase manages in "public" (Rule 5). exclude = [ "grant_usage_on_new_schema[type=function]", "grant_all_on_new_sequences[type=function]", "grant_select_on_new_objects[type=function]", ] schema { src = "file://schema.sql" } }
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.
- today First seen · 151 lines · 140 tokens per session scan A 905f543802ae
atlas-lakebase is a skill published in the GitHub repository ariga/atlas (8,805 stars, last pushed yesterday), licensed Apache-2.0. It adds 140 tokens to every session and 2,491 once invoked, about $0.0006 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 2026-11-06.
atlas-lakebase compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| atlas-lakebaseariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 140 | Claude Code |
| cloud-sql-basicsgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 108 | Claude Code, Codex |
| moai-platform-database-cloudmodu-ai/moai-adk | Skill | 1.3k | 3d ago | Apache-2.0 | A | 51 | Claude Code |
| aws-rdsTerminalSkills/skills | Skill | 192 | yesterday | Apache-2.0 | A | 107 | Claude Code, Codex |
| backup-recoveryWrongStack/WrongStack | Skill | 404 | yesterday | MIT | A | 87 | Claude Code, Codex |
| blueprint-from-collection-importreceptron/mulmoterminal | Skill | 261 | yesterday | MIT | A | 33 | Claude Code, Codex |
| huawei-cloud-rds-smart-servicehuaweicloud/huaweicloud-skills | Skill | 59 | today | MIT | A | 330 | Claude Code, Codex |