A release-preparation skill for software projects. It reviews changes, updates release notes and documentation, increments the package version, and builds the project.

Use it when preparing or publishing a release, including changelog updates, documentation checks, patch-version bumps, builds, and publish-command suggestions.

It reduces the chance of releasing without documenting changes, checking required files, or verifying that the updated project still builds.

release — Skill for Claude Code by Yesterday-AI

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 Yesterday-AI/paperclip-plugin-company-wizard --skill release

Clone the repo

git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard

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/yesterday-ai/paperclip-plugin-company-wizard/release/github.svg)](https://agentmods.dev/skills/yesterday-ai/paperclip-plugin-company-wizard/release)

Your own site

<a href="https://agentmods.dev/skills/yesterday-ai/paperclip-plugin-company-wizard/release"><img src="https://agentmods.dev/badge/skills/yesterday-ai/paperclip-plugin-company-wizard/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/yesterday-ai/paperclip-plugin-company-wizard/release"><img src="https://agentmods.dev/badge/skills/yesterday-ai/paperclip-plugin-company-wizard/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,554 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	$0.00064	$0.01554
Opus 5	$0.00032	$0.00777
Sonnet 5	$0.00013	$0.00311
Haiku 4.5	$0.00006	$0.00155

Measured 12d ago against content hash 01e952a6e179, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release — Prepare and Document a New Version

Phase 1: Analyze Changes

Understand what changed since the last release:

Read current version from package.json.
Read CHANGELOG.md to understand the last documented version and its date. Note any gap — if package.json is ahead of the changelog, intermediate releases were shipped without entries.
Find the release boundary. Try git tag -l 'v*' --sort=-v:refname | head -5 for the latest tag. If no tags exist, find the commit that last bumped the version (e.g., git log --oneline --all -- package.json | head -5) and use that SHA as the base.
Run git log <base>..HEAD to collect all commit messages since the last release.
Run git diff <base>..HEAD to see all committed file changes. Also run git diff HEAD to capture any uncommitted work in the working tree — this may contain unreleased feature work.
Count templates from the filesystem to verify against documentation:
- ls templates/presets/ | wc -l
- ls templates/modules/ | wc -l
- ls templates/roles/ | wc -l
Pay attention to:
- New features (new files, new actions, new UI steps)
- Bug fixes (error handling, logic corrections)
- Template changes (new presets, modules, roles, prompt updates)
- Configuration changes (new settings, defaults)
- Breaking changes (removed features, renamed fields, API changes)
Categorize changes into: Added, Changed, Fixed, Removed, Template system (if applicable).

Phase 2: Update CHANGELOG.md

Read CHANGELOG.md to understand the existing format and style.
If intermediate versions exist without changelog entries (e.g., package.json jumped from 0.1.0 to 0.1.2 but the changelog only has 0.1.0), create brief entries for the skipped versions too — even if they were just version bumps or metadata changes.
Add a new version section at the top (below the header), following Keep a Changelog format:

Read the full file on GitHub · 140 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.

12d ago First seen · 140 lines · 64 tokens per session scan A 01e952a6e179

Subscribe to this mod's changes

release is a skill published in the GitHub repository Yesterday-AI/paperclip-plugin-company-wizard (171 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,554 once invoked, about $0.0003 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.

Git and workflow Multi-Agent Orchestration Releases ai-agents bootstrap cli company-as-code

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

release