genblaze: Skill for Claude Code

.claude/skills/prepare-release/SKILL.md

prepare-release is a skill for Claude Code from backblaze-labs/genblaze. It costs 71 tokens per session (1,886 once invoked), scanned A, original, MIT.

A procedure for preparing a coordinated release across multiple packages in a software project. It checks which packages changed, updates versions and dependency minimums, runs release checks, and prepares a pull request without publishing anything.

In plain words
What is it for?
Use it to inspect release scope, apply required version changes, detect dependency drift, run the pre-release checks, and prepare a merge-ready release pull request.
Why use it?
It reduces mistakes when several packages must be versioned together and prevents accidental tagging or publishing before a human review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is backblaze-labs/genblaze's own configuration. It tells Claude Code how to work on genblaze itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything genblaze configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/prepare_release.py --check.

Reuse

Borrowing it

Nothing to install: this file belongs to backblaze-labs/genblaze. 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/backblaze-labs/genblaze/main/.claude/skills/prepare-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/backblaze-labs/genblaze

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 prepare-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/backblaze-labs/genblaze/prepare-release.svg)](https://agentmods.dev/skills/backblaze-labs/genblaze/prepare-release)
Your own site
<a href="https://agentmods.dev/skills/backblaze-labs/genblaze/prepare-release"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/prepare-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00071 $0.01886
Opus 5 $0.00036 $0.00943
Sonnet 5 $0.00014 $0.00377
Haiku 4.5 $0.00007 $0.00189

Measured 6d ago against content hash aff04b5313d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prepare-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 6d 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/prepare-release/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare a release wave — $ARGUMENTS

Safety boundary: the allowed-tools list above deliberately has no git tag, gh release, twine upload, or make post-release. This skill cannot tag or publish anything — without a git tag step there is no tag to push, and without gh release or twine there is nothing to trigger .github/workflows/release.yml. It goes as far as a merge-ready release PR and stops. Tagging, releasing, and post-release verification are human commands, emitted (not run) at the end.

This is a thin driver over tools/prepare_release.py, which does the actual bookkeeping (dynamic package discovery, version bumps, dependency floor sync, reserved-core-version guard — see its module docstring). For what a wave release actually IS (versioning policy, the publish pipeline graph, tag-naming convention) see RELEASING.md — this skill does not restate it. For gating one already-decided package version one at a time, use /release-check instead; this skill operates at the wave level across every package at once.

Step 1 — Scope

python3 tools/prepare_release.py --check

Read the report: which packages changed since the last tag, what version bumps and dependency-floor updates it computes, and any warnings (e.g. a connector with no entry in libs/meta/pyproject.toml). Exit 0 means nothing to prepare — stop here. Exit 1 means proceed to Step 2. Exit 2 is a hard error (bad --set/--bump, a git failure, or the reserved-core-version guard tripping) — resolve it before continuing.

Before doing anything else, confirm:

  • You're on main (git status), up to date with origin/main, and the working tree is clean.
  • git log shows the commit you're about to release from is the one you intend.

Step 2 — Apply, then cut the CHANGELOG

python3 tools/prepare_release.py --apply

This writes every version bump and dependency-floor update computed in Step 1. Pass --set <pkg>=<version> or --bump <pkg>=minor|major to override the default patch bump for any package (e.g. --set core=0.4.0 for a deliberate minor/major, or to route around the reserved-version guard intentionally).

Read the full file on GitHub · 147 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. 6d ago First seen · 147 lines · 71 tokens per session scan A aff04b5313d3

Subscribe to this mod's changes

prepare-release is a skill published in the GitHub repository backblaze-labs/genblaze (558 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,886 once invoked, about $0.0004 per session on Opus 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 2026-08-30.