A release procedure for preparing and shipping a Python project. A release is a published version of software; this procedure uses a pull request, tests, version changes, a changelog, and deployment automation.

Use it to review merged changes, choose a version number, update the changelog and lock file, open the release pull request, and ship after required tests pass.

It provides a repeatable path for checking changes and publishing a version without bypassing the project's required checks.

How paulieb89/uk-legal-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/main/.claude/skills/release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/release/github.svg)](https://agentmods.dev/skills/paulieb89/uk-legal-mcp/release)

Your own site

<a href="https://agentmods.dev/skills/paulieb89/uk-legal-mcp/release"><img src="https://agentmods.dev/badge/skills/paulieb89/uk-legal-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/paulieb89/uk-legal-mcp/release"><img src="https://agentmods.dev/badge/skills/paulieb89/uk-legal-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 573 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.

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	$0.00030	$0.00573
Opus 5.5	$0.00012	$0.00229
Sonnet 5.5	$0.00006	$0.00115
Haiku 4.5	$0.00003	$0.00057

Measured 1mo ago against content hash e144dc8be11e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release 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 1mo 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/SKILL.md · 39 lines

What it actually says

This is the procedure around the release machinery, not the machinery itself. The deterministic parts — the main ruleset requiring the "Non-live tests" check, .github/workflows/release.yml (test → preflight → PyPI trusted publishing → Fly deploy), and [tool.bumpversion] in pyproject.toml — are documented where they live. Read release.yml and CLAUDE.md's Deployment section rather than trusting a paraphrase here, and never run fly deploy by hand.

Verify main is clean and up to date with origin/main.
List merged PRs since the last tag; read each one (gh pr view) to know what's shipping and to write the CHANGELOG entry — don't just restate commit subjects.
Branch chore/prepare-X.Y.Z-release off main.
Bump the version with bump-my-version (patch/minor/major per Conventional Commits since the last tag). It doesn't touch uv.lock — re-lock and stage that too, since CI runs uv lock --check.
Add a ## [X.Y.Z] — YYYY-MM-DD entry to CHANGELOG.md in the existing style.
Open the PR, wait for the required "Non-live tests" check, squash-merge. Release prep goes through a PR like everything else — see chore/prepare-0.7.0-release (#70) and chore/0.6.1-release-prep (#51) for precedent — never commit the bump straight to main.
Pull main, tag the merged commit vX.Y.Z, push commits then push the tag separately (git push origin main doesn't carry tags).
Confirm with the user, then gh release create vX.Y.Z. From here release.yml owns everything — watch it with gh run watch --exit-status rather than re-running any of its steps by hand.
Verify what actually shipped, not just that CI is green: the PyPI JSON API for the new version, fly status//health for the deployed machine, and one or two live semantic probes of whatever the release changed (call the actual tool against production, not just a health check) — a shipped fix that isn't observably true in prod isn't done.

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.

1mo ago First seen · 39 lines · 30 tokens per session scan A e144dc8be11e

Subscribe to this mod's changes

release is a skill published in the GitHub repository paulieb89/uk-legal-mcp (20 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 573 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 2026-09-14.

CI and CD DevOps and cloud Git and workflow Legal and compliance Releases ai-skills case-law claude hansard legislation

github-cli

Apply when using the gh CLI to manage pull requests, issues, releases, or CI workflows on GitHub.

sordi-ai/skill-everything · 25 tokens

release-checklist

Create go/no-go release checklists with pre-deploy verification, staged rollout steps, monitoring checkpoints, rollback triggers, and stakeholder communication plans.

The-AI-Directory-Company/agents-and-skills · 32 tokens

devops-pipeline

Release engineering including deployment strategies, feature flags, canary releases, blue-green deployments, and rollback procedures. Trigger for release processes, feature flag implementation, or deployment strategy design.

FutureJJ/claude-skills · 40 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/ris-austria-mcp-server · 155 tokens

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

ruvnet/RuView · 27 tokens

agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes.

ruvnet/ruflo · 21 tokens

uk-legal-mcp: Skill for Claude Code