What is paw-tools-release?

A release automation tool that handles a software version update through publishing the release on GitHub.

It helps bump the version, prepare the release, and publish a new GitHub release.

It removes repetitive release steps and reduces the chance of missing part of the release process.

paw-tools-release — Skill for Claude Code by pawbytes/skill-suites

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.

Any agent

npx skills add pawbytes/skill-suites --skill paw-tools-release

Clone the repo

git clone --depth 1 https://github.com/pawbytes/skill-suites

Made for: Claude Code.

Or install utility-tools, the plugin that ships this one along with the rest of its 3 skills.

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/pawbytes/skill-suites/paw-tools-release/github.svg)](https://agentmods.dev/skills/pawbytes/skill-suites/paw-tools-release)

Your own site

<a href="https://agentmods.dev/skills/pawbytes/skill-suites/paw-tools-release"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-tools-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/pawbytes/skill-suites/paw-tools-release"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-tools-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 720 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	$0.00044	$0.00720
Opus 5.5	$0.00018	$0.00288
Sonnet 5.5	$0.00009	$0.00144
Haiku 4.5	$0.00004	$0.00072

Measured 1mo ago against content hash 81991a3685d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paw-tools-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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/detect_version_files.py, scripts/parse_commits.py, scripts/tests/test_detect_version_files.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/tools/paw-tools-release/SKILL.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 Automation

Overview

This skill automates the complete release workflow: version bumping, changelog generation, git tagging, and GitHub release creation. Act as a release engineer who ensures clean, traceable releases with informative changelogs.

Args: Accepts --headless / -H for non-interactive execution, --version <semver> to specify version explicitly, --branch <name> to set allowed release branch.

Your output: A complete release with updated version files, appended changelog, git tag, and draft GitHub release.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml if present. If config is missing, continue with sensible defaults.

Extract relevant config keys:

release_default_branch (default: main)
communication_language (default: English)

Detect --headless / -H flag. If present, set {headless_mode}=true for all stages and complete the release without user interaction.

Prerequisites

Before starting, verify:

Git repository — Must be in a git repository with at least one commit
GitHub CLI — gh must be installed and authenticated for GitHub releases
Clean working tree — Abort if uncommitted changes exist (warn in headless, prompt in interactive)

If any prerequisite fails, explain what's needed and offer to help resolve.

Workflow

Load and execute stages sequentially:

Validate → ./references/01-validate.md
Version → ./references/02-version.md
Changelog → ./references/03-changelog.md
Release → ./references/04-release.md

Each stage specifies its progression condition. If a stage fails, stop and inform the user.

Key Decisions

These guide the executing agent's judgment:

Version bump logic — If user doesn't specify version, infer from conventional commits: breaking: → major, feat: → minor, fix:/others → patch. When in doubt, ask (or patch in headless).
Branch enforcement — If configured, only allow releases from that branch. In interactive mode, let user override.
First release handling — If no previous tags exist, include all commits since repository start.
Pre-release versions — Support --pre-release beta/rc/alpha flag for pre-release versions.

Read the full file on GitHub · 71 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 71 lines · 44 tokens per session scan A 81991a3685d4

Subscribe to this mod's changes

paw-tools-release is a skill published in the GitHub repository pawbytes/skill-suites (114 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 720 once invoked, about $0.0002 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 2026-09-03.

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

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

paw-tools-release