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.
git clone --depth 1 https://github.com/exmergo/dexWrote 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/plugins/exmergo/dex/gemini-extension)<a href="https://agentmods.dev/plugins/exmergo/dex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/exmergo/dex/gemini-extension/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/plugins/exmergo/dex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/exmergo/dex/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dex 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.
What it actually says
{
"name": "dex",
"version": "1.13.3",
"description": "Analytics engineering for Claude Code and any agent: data warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance on dbt."
}
What ships with it
43 files beside gemini-extension.json 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.
- references/bigquery.md 14 KB
- references/canonical-model.md 9.2 KB
- references/clickhouse.md 20 KB
- references/command-contract.md 101 KB
- references/cost-controls.md 12 KB
- references/databricks.md 9.0 KB
- references/dbt-project.md 10 KB
- references/duckdb.md 8.1 KB
- references/evaluation.md 5.7 KB
- references/host-integration.md 22 KB
- references/methodology.md 23 KB
- references/ossie-compatibility.md 13 KB
- references/ossie-walkthrough.md 24 KB
- references/pii-policy.md 7.7 KB
- references/postgres.md 9.8 KB
- references/project.md 45 KB
- references/redshift.md 14 KB
- references/semantic-layer.md 61 KB
- references/snowflake.md 12 KB
- references/storage.md 28 KB
- scripts/build_docs_site.py 55 KB runs code
- scripts/check_changelog_fragments.py 5.3 KB runs code
- scripts/check_container_hardening.sh 3.5 KB runs code
- scripts/check_mermaid_syntax.mjs 3.0 KB runs code
- scripts/check_no_em_dashes.py 5.9 KB runs code
- scripts/clickhouse_cloud/preflight.sh 3.0 KB runs code
- scripts/clickhouse_cloud/README.md 4.8 KB
- scripts/clickhouse_cloud/run_integration.sh 1.1 KB runs code
- scripts/clickhouse_cloud/secrets.sh 4.8 KB runs code
- scripts/clickhouse_cloud/teardown.sh 3.9 KB runs code
- scripts/clickhouse_local_users.sql 994 B
- scripts/clickhouse_seed.sql 10 KB
- scripts/dump_mermaid_fixtures.py 11 KB runs code
- scripts/postgres_seed.sql 6.6 KB
- scripts/prepare_release.sh 5.4 KB runs code
- scripts/setup_bigquery_ci.sh 6.0 KB runs code
- scripts/setup_clickhouse_cloud_ci.sh 22 KB runs code
- scripts/setup_clickhouse_dev.sh 4.8 KB runs code
- scripts/setup_databricks_ci.sh 9.0 KB runs code
- scripts/setup_postgres_dev.sh 3.3 KB runs code
- scripts/setup_redshift_ci.sh 19 KB runs code
- scripts/setup_snowflake_ci.sh 12 KB runs code
- scripts/testpypi_dry_run.sh 3.4 KB runs code
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 Changed 6dde828ead28
- yesterday First seen · 6 lines scan A d7c5b3987f98
dex is a plugin published in the GitHub repository exmergo/dex (85 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-15.
Other plugins, from other repositories
ecto
Compatibility namespace for the Elixir/Phoenix plugin's /ecto: commands.
mirrord
Connect your agent to a live Kubernetes cluster with mirrord, so it tests code changes against real services. Covers setup, config, CI, database branching, queue splitting, and preview environments.
data-engineering
Analytics engineering, dbt patterns, BigQuery optimization, data quality, and pipeline workflows.
cc-notify-hooks
A notification plugin for coding agents such as Claude Code, Codex, DeepSeek Harness, and Reasonix. It sends short waiting updates through several notification channels and handles longer updates asynchronously.
sql
SQL specialist: query optimization, schema and index design, execution-plan analysis, and platform-specific features across PostgreSQL, MySQL, SQL Server, SQLite, and Oracle.
motherduck-skills
MotherDuck skills for agents and developers: use the CLI and Guides, explore schemas, write DuckDB SQL, build Dives and Flights, and ship analytics apps and pipelines.