An automated release procedure for publishing the notebooklm-mcp-2026 Python package to PyPI, the public package repository for Python. It checks the project, updates its version, and proceeds through the release steps in order.

Use it to run pre-release linting and tests, verify Git and GitHub access, choose a patch, minor, or major version change, and publish a new package version.

It turns a release into a repeatable checklist and stops when tests, code checks, authentication, or repository cleanliness fail.

release — Command by Faxtom

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/faxtom/notebooklm-mcp/release

Clone the repo

git clone --depth 1 https://github.com/Faxtom/notebooklm-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 615 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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	$0.00000	$0.00615
Opus 5	$0.00000	$0.00308
Sonnet 5	$0.00000	$0.00123
Haiku 4.5	$0.00000	$0.00061

Measured yesterday against content hash 73a231d36e84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

Origin

This is a copy

100% identical to release — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/release.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release a new version of notebooklm-mcp-2026 to PyPI.

Instructions

You are automating the release process for the notebooklm-mcp-2026 Python package. Follow these steps in order. If any step fails, stop immediately and report the error — do NOT proceed to later steps.

Step 1: Pre-flight checks

Run these in parallel:

ruff check src/ tests/ — lint must pass
pytest -v --tb=short — all tests must pass
git status — working tree must be clean (no uncommitted changes). If there are uncommitted changes, stop and ask the user to commit or stash them first.
gh auth status — GitHub CLI must be authenticated

If any check fails, stop and report the issue.

Step 2: Determine version

Read the current version from pyproject.toml (the version field under [project]).

Ask the user what kind of bump they want:

patch (e.g. 0.1.2 → 0.1.3) — bug fixes, small changes
minor (e.g. 0.1.2 → 0.2.0) — new features, non-breaking
major (e.g. 0.1.2 → 1.0.0) — breaking changes

Compute the new version number. Show the user: Current: X.Y.Z → New: A.B.C and confirm before proceeding.

Step 3: Bump version

Edit pyproject.toml and change the version field to the new version.

Step 4: Commit and tag

git add pyproject.toml
git commit -m "Release v{NEW_VERSION}"
git tag v{NEW_VERSION}

Step 5: Push

git push origin master
git push origin v{NEW_VERSION}

Note: The main branch is master. Push both the commit and the tag.

Step 6: Create GitHub release

gh release create v{NEW_VERSION} --title "v{NEW_VERSION}" --generate-notes

Step 7: Watch pipeline

Run gh run watch to monitor the CI + publish pipeline. Wait for it to complete.

If the pipeline fails:

Report the failure
Do NOT delete the tag or release automatically — ask the user what they want to do

Step 8: Verify

Run gh run list --limit 3 to confirm the release workflow succeeded.

Tell the user:

The new version v{NEW_VERSION} has been released
PyPI page: https://pypi.org/project/notebooklm-mcp-2026/{NEW_VERSION}/
GitHub release: the URL from gh release view v{NEW_VERSION} --json url

Read the full file on GitHub · 71 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.

yesterday First seen · 71 lines · 0 tokens per session scan A 73a231d36e84

Subscribe to this mod's changes

release is a command published in the GitHub repository Faxtom/notebooklm-mcp (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 615 tokens. A static security scan graded it A with 0 findings. It is 100% identical to release, differing in 0 lines, and is treated as a copy.

Git and workflow Languages Testing

release