release

release is a command for Claude Code from sprine/ontario-data-mcp. It costs 16 tokens per session (1,226 once invoked), scanned C, original, MIT.

A release command for Python packages published to PyPI, the main public package repository for Python. It checks the Git state, changes the version, runs tests, commits, pushes, and publishes.

In plain words
What is it for?
Making patch, minor, or major version releases from the main branch after verifying a clean working tree and passing tests.
Why use it?
It puts the required release checks and publishing steps into one repeatable process.

Command for Claude Code

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 commands/sprine/ontario-data-mcp/release
Clone the repo
git clone --depth 1 https://github.com/sprine/ontario-data-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

README.md
[![agentmods](https://agentmods.dev/badge/commands/sprine/ontario-data-mcp/release.svg)](https://agentmods.dev/commands/sprine/ontario-data-mcp/release)
Your own site
<a href="https://agentmods.dev/commands/sprine/ontario-data-mcp/release"><img src="https://agentmods.dev/badge/commands/sprine/ontario-data-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00016 $0.01226
Opus 5 $0.00008 $0.00613
Sonnet 5 $0.00003 $0.00245
Haiku 4.5 $0.00002 $0.00123

Measured 4d ago against content hash 1012b3d4e4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

release scanned grade C 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist && uv build
.claude/commands/release.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Bump the version, run tests, commit, push, and publish to PyPI.

The first argument is the bump type: patch (default), minor, or major. Everything after the bump type is used as the commit message body. If no message is provided, generate one from the staged and unstaged changes.

Steps

1. Preflight checks

Verify the working tree is ready for release. Stop immediately if any check fails.

# Must be on main
[ "$(git branch --show-current)" = "main" ] || { echo "ERROR: not on main"; exit 1; }

# Working tree must be clean (no staged or unstaged changes)
git diff --quiet && git diff --cached --quiet || { echo "ERROR: dirty working tree"; exit 1; }

2. Determine version bump

Parse $ARGUMENTS for the bump type. Default to patch if not specified or if the first word isn't patch/minor/major.

Read the current version from pyproject.toml and compute the new version:

  • patch: 0.1.7 → 0.1.8
  • minor: 0.1.7 → 0.2.0
  • major: 0.1.7 → 1.0.0

Verify the tag v{new_version} does not already exist:

git tag -l "v{new_version}" | grep -q . && { echo "ERROR: tag v{new_version} already exists"; exit 1; }

3. Run tests

uv run pytest

Stop immediately if any tests fail. This covers:

  • All unit tests
  • Doc-accuracy checks (tool/resource counts, licence attribution, version consistency)

4. Live smoke test (optional)

uv run pytest -m live --live -v

This runs tests/test_live_smoke.py and tests/test_arcgis_smoke.py against real government APIs. Stop if any assertion fails.

Skip if the APIs are down or you're releasing a docs-only change.

5. Build

Build early so a failure doesn't leave a tagged commit with no PyPI release.

rm -rf dist && uv build

6. Bump version and update changelog

Edit pyproject.toml to set the new version. Then update the lockfile:

uv lock && uv sync

Add a new entry to CHANGELOG.md at the top (below the header). Follow the existing format:

Read the full file on GitHub · 164 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. 4d ago First seen · 164 lines · 16 tokens per session scan C 1012b3d4e4ef

Subscribe to this mod's changes

release is a command published in the GitHub repository sprine/ontario-data-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,226 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.