agentmods.dev

release

release is a skill for Claude Code, Codex from galaxyproject/galaxy-mcp. It costs 61 tokens per session (3,343 once invoked), scanned C, original, MIT.

A guarded release procedure for galaxy-mcp, a Python package published to PyPI, the main public package index for Python libraries.

In plain words
What is it for?
Use it to update the package version, refresh the lockfile, prepare the GitHub release, and pause for approval before pushing or publishing.
Why use it?
It reduces the risk of publishing the wrong version or releasing accidentally, especially because PyPI uploads cannot be replaced.

Skill for Claude CodeCodex

not rated 38 24d ago C scan 61 tokens original MIT
View the source file galaxyproject/galaxy-mcp
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/galaxyproject/galaxy-mcp/release
Any agent
npx skills add galaxyproject/galaxy-mcp --skill release
Clone the repo
git clone --depth 1 https://github.com/galaxyproject/galaxy-mcp

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/galaxyproject/galaxy-mcp/release.svg)](https://agentmods.dev/skills/galaxyproject/galaxy-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/galaxyproject/galaxy-mcp/release"><img src="https://agentmods.dev/badge/skills/galaxyproject/galaxy-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,343 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00061 $0.03343
Opus 5 $0.00030 $0.01672
Sonnet 5 $0.00012 $0.00669
Haiku 4.5 $0.00006 $0.00334

Measured 5d ago against content hash bc4899af6efa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

release scanned grade C with 2 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s https://pypi.org/pypi/galaxy-mcp/json | python3 -c "import sys,json;print(json.load(sys.stdin)['info']['version'])" # expect $NEW

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://pypi.org/pypi/galaxy-mcp/json | python3 -c "import sys,json;print(json.load(sys.stdin)['info']['version'])" # expect $NEW
.claude/skills/release/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release (galaxy-mcp)

Overview

Cut a galaxy-mcp release end to end. The package publishes to PyPI, which is irreversible -- a version string can never be re-uploaded. The trigger is publishing the GitHub release: python-release.yml runs on release: published, builds, and twine uploads to PyPI. Two actions are outward-facing and gated -- the push of the version-bump commit to galaxyproject/main and the release publish (the PyPI trigger). STOP for an explicit human "go" before each. Everything before the push is local and reversible.

Why use this over hand-running commands: it gets the version right (the .dev0 marker on main is the source of truth, NOT release-drafter's auto-guess), it uses uv lock for the lockfile instead of a foot-gun sed, and it gates the publish so nothing ships on autopilot.

Violating the letter of the gates is violating the spirit. Don't collapse the flow into one script. Stop, show, and wait for a human "go" before each publish boundary.

Layout / facts (easy to get wrong)

  • The Python package lives in mcp-server-galaxy-py/, not the repo root. Three files carry the version: pyproject.toml, src/galaxy_mcp/__init__.py, and uv.lock.
  • main between releases carries a dev version like X.Y.0.dev0. The release version = that minus .dev0 (e.g. 1.7.0.dev0 -> 1.7.0). The dev marker is the intent.
  • Releases are cut from galaxyproject/main. The primary checkout is often on a feature branch -- always work from a clean worktree off canonical main, never in place.
  • release-drafter keeps a DRAFT release, but it resolves the version from PR labels and under-resolves to a patch when PRs lack a feature/minor label (it drafted v1.6.1 when the real release was 1.7.0). Trust the .dev0 marker, not the draft tag.

Modes

  • /release -- full guided run.
  • /release preview -- Phase 0-1 only: determine version + gather notes, then STOP. Writes/pushes nothing.
  • /release <version> -- pin the version (e.g. 1.7.0) instead of deriving it.

Read the full file on GitHub · 228 lines

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. 5d ago First seen · 228 lines · 61 tokens per session scan C bc4899af6efa

Subscribe to this mod's changes

release is a skill published in the GitHub repository galaxyproject/galaxy-mcp (38 stars, last pushed 24d ago), licensed MIT. It adds 61 tokens to every session and 3,343 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowReleases
Related

Other skills, from other repositories

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm.

ruvnet/ruflo · 19 tokens

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

openai/symphony · 42 tokens

changelog

Create changelog files for important commits in a PR.

pipecat-ai/pipecat · 13 tokens

multi-agent-release-manager

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

chromium/chromium · 27 tokens

refresh-arm-sdk-release

WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…

Azure/azure-sdk-for-net · 91 tokens