dex icon

dex

exmergo/dex · v1.18.0 · Tools & Integrations

Agent skills for warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance.

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is dex a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Agent Plugin
  • Agent Skills
  • Claude Code
  • Antigravity CLI
  • 6 skills

Before you install

Sign-in
Asks you to sign in when you install it
Declared access
Not declared
License
Apache-2.0

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is dex?

dex is a published tools & integrations plugin for AI coding agents that works with Agent Plugin, Agent Skills, Claude Code and Antigravity CLI, developed by exmergo and distributed through the HOL AI plugin registry. Agent skills for warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance.

Canonical slug
exmergo/dex
Version
v1.18.0 · updated Nov 19, 2026

Registry snapshot

Owner verification
Not verified
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
6 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

79

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
65/100
MCP server setup
100/100
Plugin Security
96/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/exmergo/dex
Source commit
445acb2fe4e0…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Ready (structural check)

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Partial scan
Security result
96
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-75Mgyc / cisco-skill-scanner: failedcodex:hol-plugin-scanner-75Mgyc / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

N/A

5 checks · not applicable

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

25/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

N/A

5 checks · not applicable

[codex:.] Best Practices

12/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

16/16

6 checks

[gemini:.] Operational Security

N/A

5 checks · not applicable

[gemini:.] Code Quality

10/10

2 checks

Published advisories

  • GHSA-28xv-9wpg-c42rGitHub security advisoriesPublished

    Hosted Semantic Layer sends the dbt Cloud token to any host named in .dex/config.yml

  • GHSA-f3jf-cv9h-7c3gGitHub security advisoriesPublished

    explore query firewall admits file-reading and network functions and leaves WHERE subqueries unresolved

  • GHSA-jm75-qwf5-vg52GitHub security advisoriesPublished

    Envelope errors and warnings are printed unredacted, and skill warm-up copies uv stderr into them

GitHub security advisories are those the source repository has published. Checked .

Findings

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Find the marketplace and plugin names

    The install id is <plugin-entry>@<marketplace-name>, and the marketplace name is declared inside the manifest — it can differ from the repository name. List registered marketplaces to read both names.

    shell
  3. 3

    Install the plugin

    Substitute the plugin entry name and the marketplace name shown by the previous step.

    claude code

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "dex",
  "version": "1.18.0",
  "description": "Analytics engineering for Claude Code and any agent: data warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance on dbt.",
  "author": {
    "name": "Exmergo, Inc.",
    "email": "[email protected]",
    "url": "https://www.exmergo.com"
  },
  "homepage": "https://docs.exmergo.com/dex",
  "repository": "https://github.com/exmergo/dex",
  "license": "Apache-2.0",
  "keywords": [
    "analytics-engineering",
    "dbt",
    "claude-code",
    "text-to-sql",
    "semantic-layer",
    "duckdb",
    "snowflake",
    "bigquery",
    "databricks",
    "data-engineering",
    "agent",
    "metricflow",
    "schema-drift",
    "data-contracts",
    "redshift",
    "postgres",
    "clickhouse",
    "trino"
  ],
  "interface": {
    "displayName": "dex",
    "developerName": "exmergo"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/exmergo/dex
Marketplace path
Unknown
Source path
plugins/exmergo/dex
Install policy
AVAILABLE

Skills

6 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • explore

    claude/skills/explore/SKILL.md

    Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: inventory, column profiles, PII detection, grain and data-quality problems, verified joins, ER diagrams, ad-hoc SQL probes, segmentation, and the semantic layer a repo declares (dbt, Ossie, SLayer, or Cube). Trigger it on an unmet precondition, not on phrasing: if you are about to write or fix SQL against tables whose columns, types, grain, or join keys you have not verified in this session, use this FIRST. That includes dbt work (building a model, fixing one, debugging wrong numbers) whenever the ticket names source tables without spelling out their schema. It applies mid-task too: on reaching a table you have not inspected, stop and use this rather than guess column names. Also for "what''s in my duckdb", "is this data any good", "how do these tables relate". Read-only; writes only the .dex/ cache. It does not author the model: transform does, and maintain reconciles a project that has drifted.

    Raw SKILL.md
  • maintain

    claude/skills/maintain/SKILL.md

    Use this to find out whether an existing dbt project or semantic layer (dbt, Ossie, SLayer or Cube) is correct against its warehouse, and if not, why. `maintain verify` checks the project as it stands; against a .dex/ snapshot, `maintain check` finds schema, volume, grain, and semantic drift and `maintain reconcile` proposes the fix. Reach for it whenever an existing project is suspected wrong, whether or not anything is known to have changed: "this model is wrong, work out why", "the numbers look too high", "some rows are missing", "this column is empty", "duplicates in my fact table", "the project is broken", "diagnose why this test fails", "a test fails and nobody changed the model", "which models have no tests", "how good is our test coverage", "did anything drift", "the metric definition changed". Read-only; fixes come back as reviewable diffs and never overwrite hand-written work. Writing the fix, or repairing a model you just edited, is transform''s; a data question with no project is explore''s.

    Raw SKILL.md
  • transform

    claude/skills/transform/SKILL.md

    Use this to author and change a dbt project or a semantic layer: bootstrap a project (`transform init`), write or refactor models from staging to marts, add tests and docs, and define semantic models, entities, dimensions, and metrics in MetricFlow, Apache Ossie or SLayer YAML. Reach for it instead of editing model files by hand whenever a change spans more than one file or must stay consistent with the project: it validates the edit against the real schema, returns a reviewable diff with a plan id, and catches what otherwise fails at `dbt run`, such as wrong columns or broken refs. Bug-fix tickets count: "this model returns wrong numbers, fix it" is a transform task. Also for "build a staging model for this table", "define a revenue metric", "add a dimension to this entity". Warehouse builds are dev-target only, gated, and cost-surfaced first. If you have not verified the source tables'' columns or grain, use explore first. For a project that drifted from the warehouse, use maintain.

    Raw SKILL.md
  • explore

    skills/explore/SKILL.md

    Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: inventory, column profiles, PII detection, grain and data-quality problems, verified joins, ER diagrams, ad-hoc SQL probes, segmentation, and the semantic layer a repo declares (dbt, Ossie, SLayer, or Cube). Trigger it on an unmet precondition, not on phrasing: if you are about to write or fix SQL against tables whose columns, types, grain, or join keys you have not verified in this session, use this FIRST. That includes dbt work (building a model, fixing one, debugging wrong numbers) whenever the ticket names source tables without spelling out their schema. It applies mid-task too: on reaching a table you have not inspected, stop and use this rather than guess column names. Also for "what''s in my duckdb", "is this data any good", "how do these tables relate". Read-only; writes only the .dex/ cache. It does not author the model: transform does, and maintain reconciles a project that has drifted.

    Raw SKILL.md
  • maintain

    skills/maintain/SKILL.md

    Use this to find out whether an existing dbt project or semantic layer (dbt, Ossie, SLayer or Cube) is correct against its warehouse, and if not, why. `maintain verify` checks the project as it stands; against a .dex/ snapshot, `maintain check` finds schema, volume, grain, and semantic drift and `maintain reconcile` proposes the fix. Reach for it whenever an existing project is suspected wrong, whether or not anything is known to have changed: "this model is wrong, work out why", "the numbers look too high", "some rows are missing", "this column is empty", "duplicates in my fact table", "the project is broken", "diagnose why this test fails", "a test fails and nobody changed the model", "which models have no tests", "how good is our test coverage", "did anything drift", "the metric definition changed". Read-only; fixes come back as reviewable diffs and never overwrite hand-written work. Writing the fix, or repairing a model you just edited, is transform''s; a data question with no project is explore''s.

    Raw SKILL.md
  • transform

    skills/transform/SKILL.md

    Use this to author and change a dbt project or a semantic layer: bootstrap a project (`transform init`), write or refactor models from staging to marts, add tests and docs, and define semantic models, entities, dimensions, and metrics in MetricFlow, Apache Ossie or SLayer YAML. Reach for it instead of editing model files by hand whenever a change spans more than one file or must stay consistent with the project: it validates the edit against the real schema, returns a reviewable diff with a plan id, and catches what otherwise fails at `dbt run`, such as wrong columns or broken refs. Bug-fix tickets count: "this model returns wrong numbers, fix it" is a transform task. Also for "build a staging model for this table", "define a revenue metric", "add a dimension to this entity". Warehouse builds are dev-target only, gated, and cost-surfaced first. If you have not verified the source tables'' columns or grain, use explore first. For a project that drifted from the warehouse, use maintain.

    Raw SKILL.md

File inventory

.claude-plugin/plugin.json

file

1,022 bytes

a86325c0c90a704e…

.codex-plugin/plugin.json

plugin-manifest

867 bytes

7ccaa9fee9b28632…

.codexignore

file

224 bytes

14a0be79a215405d…

.cursor/rules/dex.mdc

file

783 bytes

1210358bb17b4e85…

.github/dependabot.yml

file

3,792 bytes

f19fc5b366169cad…

.windsurf/rules/dex.md

file

725 bytes

c9d95ff52689c0b6…

AGENTS.md

file

237,594 bytes

91c6f559e1ba4997…

claude/skills/explore/evals/evals.json

file

13,885 bytes

20015954690cea7a…

claude/skills/explore/references/commands.md

file

33,985 bytes

f7793ec0266ff709…

claude/skills/explore/references/connectors.md

file

7,040 bytes

cc2f9e18d807c2f8…

claude/skills/explore/references/probe-playbook.md

file

9,231 bytes

0e9fd2f56d405ead…

claude/skills/explore/references/semantic-playbook.md

file

23,072 bytes

b5c627766634a6a2…

claude/skills/explore/scripts/run.py

file

31,749 bytes

f491891e4d2404bc…

claude/skills/explore/SKILL.md

skill

40,353 bytes

37603c5a1d9fb381…

claude/skills/maintain/evals/evals.json

file

9,582 bytes

b7e6fd190d6042be…

claude/skills/maintain/references/axes.md

file

52,772 bytes

ad5136fa0ade8e28…

claude/skills/maintain/scripts/run.py

file

31,749 bytes

f491891e4d2404bc…

claude/skills/maintain/SKILL.md

skill

44,110 bytes

982a814c3ef8989c…

claude/skills/transform/evals/evals.json

file

14,817 bytes

579fc026295d9a5f…

claude/skills/transform/references/commands.md

file

83,320 bytes

1dcf47f2abfbea90…

claude/skills/transform/references/declarations.md

file

70,147 bytes

8c2618bfb2b5a9d1…

claude/skills/transform/references/edit-kinds.md

file

5,787 bytes

73401a6ceb70d255…

claude/skills/transform/references/feature-retirement.md

file

11,971 bytes

56bd06989d407af9…

claude/skills/transform/references/feature-toggles.md

file

12,464 bytes

da5f3776cd5dc082…

claude/skills/transform/references/incremental-repairs.md

file

10,105 bytes

ce9201a7145de1ce…

claude/skills/transform/references/init-and-dev-target.md

file

6,571 bytes

934117dbf8f67a68…

claude/skills/transform/references/macros.md

file

2,142 bytes

8e59ebc6cdedc48d…

claude/skills/transform/references/model-versions.md

file

9,257 bytes

d45febafb60d509d…

claude/skills/transform/references/prerequisite-repairs.md

file

18,417 bytes

2b8fe5824fe357d0…

claude/skills/transform/references/semantic-layer.md

file

25,269 bytes

9aef2a8ab4ce02d9…

claude/skills/transform/references/test-strength.md

file

5,896 bytes

fd370cb514f5d7fe…

claude/skills/transform/scripts/run.py

file

31,749 bytes

f491891e4d2404bc…

claude/skills/transform/SKILL.md

skill

51,413 bytes

c34e467a334dbef6…

gemini-extension.json

file

223 bytes

429efcacb332946d…

LICENSE

file

15,124 bytes

fdbe035da911b994…

plugin.json

file

887 bytes

7fc9de94aed32268…

README.md

file

32,521 bytes

44a577ccda666d0b…

SECURITY.md

file

2,714 bytes

80509a32d64981a6…

skills/explore/evals/evals.json

skill

13,885 bytes

20015954690cea7a…

skills/explore/references/commands.md

skill

36,449 bytes

f42669f44d86c374…

skills/explore/references/connectors.md

skill

7,040 bytes

cc2f9e18d807c2f8…

skills/explore/references/probe-playbook.md

skill

9,231 bytes

0e9fd2f56d405ead…

skills/explore/references/semantic-playbook.md

skill

25,985 bytes

0c69a65a265b834e…

skills/explore/scripts/run.py

skill

32,495 bytes

9977af58ef8ae79c…

skills/explore/SKILL.md

skill

41,252 bytes

f426575d0f779bbc…

skills/maintain/evals/evals.json

skill

9,582 bytes

b7e6fd190d6042be…

skills/maintain/references/axes.md

skill

53,717 bytes

bdc44a41427a1dc1…

skills/maintain/scripts/run.py

skill

32,495 bytes

9977af58ef8ae79c…

skills/maintain/SKILL.md

skill

44,382 bytes

981621d4d6328cdc…

skills/transform/evals/evals.json

skill

14,817 bytes

579fc026295d9a5f…

skills/transform/references/commands.md

skill

85,157 bytes

c5ede544fe624fd8…

skills/transform/references/declarations.md

skill

72,076 bytes

9e666fac0eddd22b…

skills/transform/references/edit-kinds.md

skill

6,086 bytes

6202da9fb63d588d…

skills/transform/references/feature-retirement.md

skill

11,971 bytes

56bd06989d407af9…

skills/transform/references/feature-toggles.md

skill

12,464 bytes

da5f3776cd5dc082…

skills/transform/references/incremental-repairs.md

skill

10,105 bytes

ce9201a7145de1ce…

skills/transform/references/init-and-dev-target.md

skill

6,571 bytes

934117dbf8f67a68…

skills/transform/references/macros.md

skill

2,142 bytes

8e59ebc6cdedc48d…

skills/transform/references/model-versions.md

skill

9,257 bytes

d45febafb60d509d…

skills/transform/references/prerequisite-repairs.md

skill

18,417 bytes

2b8fe5824fe357d0…

skills/transform/references/semantic-layer.md

skill

25,269 bytes

9aef2a8ab4ce02d9…

skills/transform/references/test-strength.md

skill

5,896 bytes

fd370cb514f5d7fe…

skills/transform/scripts/run.py

skill

32,495 bytes

9977af58ef8ae79c…

skills/transform/SKILL.md

skill

52,443 bytes

eb86793fe5d54290…

dex — Frequently asked questions

What is dex?
dex is an AI plugin in the HOL registry. Agent skills for warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance.
How do I install dex?
Install dex in your harness: Claude Code — /plugin marketplace add exmergo/dex; Antigravity CLI — npx [email protected] add exmergo/dex; Any agent — npx [email protected] add exmergo/dex. Full step-by-step guidance is on the HOL plugin page.
How do I install dex in Claude Code?
To install dex in Claude Code, start with /plugin marketplace add exmergo/dex. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install dex in Antigravity CLI?
To install dex in Antigravity CLI, start with npx [email protected] add exmergo/dex. The complete step-by-step install guide for Antigravity CLI is on the HOL plugin page.
How is the Trust Score for dex computed?
dex has a HOL Trust Score of 79 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/exmergo%2Fdex/trust
Who publishes dex?
dex is published by exmergo and listed on HOL.

Directory acceptance

Listed in 1 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins