A release checklist for the garmin-coach-mcp package, covering version changes, Git tags, automated publishing, and authentication between two GitHub accounts.

Use it to bump the package version, run packaging tests, commit and tag changes, push to GitHub, and publish the package to PyPI and the MCP registry.

It reduces the risk of missing one of the three required version updates or publishing from the wrong account. It also checks tests, branch status, and changelog details before release.

How snoozelieb/coach-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to snoozelieb/coach-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/snoozelieb/coach-mcp/main/.claude/skills/release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/snoozelieb/coach-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/release/github.svg)](https://agentmods.dev/skills/snoozelieb/coach-mcp/release)

Your own site

<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/release"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/release/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/release"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 731 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00731
Opus 5	$0.00032	$0.00365
Sonnet 5	$0.00013	$0.00146
Haiku 4.5	$0.00006	$0.00073

Measured 8d ago against content hash b6e23be83de3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

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

curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.snoozelieb/coach-mcp"

.claude/skills/release/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing garmin-coach-mcp

Full runbook: docs/PUBLISHING.md. This skill is the operational checklist with the machine-specific facts that are NOT in the runbook.

Preflight

git branch --show-current must be main, tree clean, up to date with origin.
Full suite green locally: python -m pytest -q.
CHANGELOG.md [Unreleased] section describes what ships.

1. Version triple-bump (test-enforced)

Bump ALL THREE, or tests/test_packaging.py fails:

pyproject.toml → version
server.json → both version fields (top level AND packages[0])
CHANGELOG.md → retitle [Unreleased] to ## [x.y.z] - YYYY-MM-DD

Run python -m pytest tests/test_packaging.py -q to confirm, then commit.

2. Push + tag — the auth dance (IMPORTANT)

The machine has two GitHub accounts (snoozelieb owns this repo; the default gh account is a work account that cannot push here or create releases). The repo has a local credential.helper = !gh auth git-credential. The user does NOT want browser auth flows (password manager). Run these via the Bash tool, NOT PowerShell, and never compound the commands:

gh auth switch --user snoozelieb
git push origin main
git tag vX.Y.Z
git push origin vX.Y.Z
gh auth switch    # ALWAYS switch back afterwards (no --user needed: toggles to the other account)

The tag push triggers .github/workflows/release.yml: builds sdist+wheel (verifies tag matches pyproject.toml), publishes to PyPI via trusted publishing (OIDC, no tokens), creates the GitHub Release with the CHANGELOG excerpt. Note: the local gh default is the work account, which cannot create releases on this repo — that's why CI does it.

3. Verify

Actions → Release run is green.
https://pypi.org/project/garmin-coach-mcp/ shows the new version.
GitHub Release exists with wheel + sdist.

4. MCP Registry (manual, user-run)

Separate from CI. From the repo root (where server.json lives):

mcp-publisher login github     # device-code flow — ask the USER to run this (interactive)
mcp-publisher publish

Read the full file on GitHub · 74 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.

8d ago First seen · 74 lines · 63 tokens per session scan A b6e23be83de3

Subscribe to this mod's changes

release is a skill published in the GitHub repository snoozelieb/coach-mcp (2 stars, last pushed 12d ago), licensed MIT. It adds 63 tokens to every session and 731 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Releases

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

multi-agent-release-manager

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

chromium/chromium · 27 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

pack-submit

Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.

aeonfun/aeon · 27 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens

updater_guide

Guidance for checking for and installing Row-Bot updates.

siddsachar/row-bot · 17 tokens

coach-mcp: Skill for Claude Code