agentmods.dev

dbt-mcp: Skill for Claude Code

.claude/skills/release-dbt-mcp/SKILL.md

release-dbt-mcp is a skill for Claude Code from dbt-labs/dbt-mcp. It costs 18 tokens per session (324 once invoked), scanned A, original, Apache-2.0.

A release procedure for dbt-mcp, a package that connects dbt data workflows to other tools, and publishes new versions to PyPI, Python’s package repository.

In plain words
What is it for?
Use it to start the release workflow, monitor GitHub actions, complete the required environment approval, and verify the package appears on PyPI.
Why use it?
It provides the required sequence for creating, approving, merging, and checking a release instead of handling those steps ad hoc.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is dbt-labs/dbt-mcp's own configuration. It tells Claude Code how to work on dbt-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dbt-mcp configures →

not rated 616repo +3 yesterday A scan SkillSpector: pass 18 tokens original Apache-2.0
View source ↗ dbt-labs/dbt-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to dbt-labs/dbt-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dbt-labs/dbt-mcp/main/.claude/skills/release-dbt-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dbt-labs/dbt-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 release-dbt-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/dbt-labs/dbt-mcp/release-dbt-mcp/github.svg)](https://agentmods.dev/skills/dbt-labs/dbt-mcp/release-dbt-mcp)
Your own site
<a href="https://agentmods.dev/skills/dbt-labs/dbt-mcp/release-dbt-mcp"><img src="https://agentmods.dev/badge/skills/dbt-labs/dbt-mcp/release-dbt-mcp/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.

agentmods 80×15 button for release-dbt-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/dbt-labs/dbt-mcp/release-dbt-mcp"><img src="https://agentmods.dev/badge/skills/dbt-labs/dbt-mcp/release-dbt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00018 $0.00324
Opus 5.5 $0.00007 $0.00130
Sonnet 5.5 $0.00004 $0.00065
Haiku 4.5 $0.00002 $0.00032

Measured 2mo ago against content hash 7d8348f4d1a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-dbt-mcp 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 2mo 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.

.claude/skills/release-dbt-mcp/SKILL.md · 15 lines

What it actually says

  1. Initiate the Create release PR GitHub workflow. Use the auto for the bump input. Don't set the prerelease input.
  2. Wait for this to start and then poll the status of this running workflow.
  3. Once it finishes successfully, approve & squash merge (gh pr merge --squash --admin) the PR that was created. This repo does not allow merge commits. This is an autogenerated PR, so it is okay to bypass CI. This is the only case that bypassing CI is okay.
  4. Merging this PR will kick off the Release dbt-mcp workflow.
  5. Wait for this to start and then poll the status of this running workflow. When the workflow waits for GitHub environment approval, open the page with open <url>
  6. Ask the user to continue once they have approved the GitHub environment.
  7. Once the user continues, continue polling the status of the Release dbt-mcp workflow.
  8. When that workflow has finished successfully. Ensure that the new version of dbt-mcp is on PyPI by checking the JSON API at https://pypi.org/pypi/dbt-mcp/json (the HTML page is JS-rendered and won't work with WebFetch).
  9. Report to the user the status of all GitHub workflows that ran and the status of the release.
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. 2mo ago First seen · 15 lines · 18 tokens per session scan A 7d8348f4d1a8

Subscribe to this mod's changes

release-dbt-mcp is a skill published in the GitHub repository dbt-labs/dbt-mcp (616 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 324 once invoked, about $0.0001 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 2026-08-30.

DevOps and cloudGit and workflowLLMReleasesdata-analyticsdata-engineeringmcpmcp-servermodel-context-protocol
Related

release-dbt-mcp compared with skills from other repositories

release-dbt-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
release-dbt-mcpdbt-labs/dbt-mcpSkill616yesterdayApache-2.0A18Claude Code
polish-docs-metacyanheads/git-mcp-serverSkill2451mo agoApache-2.0A53Claude Code, Codex
release-and-publishcyanheads/git-mcp-serverSkill2451mo agoApache-2.0A83Claude Code, Codex
studio-source-controlserac-labs/seracSkill7717d agoApache-2.0A59Claude Code
update-set-workflowserac-labs/seracSkill7717d agoApache-2.0A46Claude Code
hmem-releaseBumblebiber/hmemSkill246d agoMITA50Claude Code
publish-releaseByggarepop/dotnet-mcp-orchestratorSkill217d agoMITA63Claude Code, Codex