A release workflow for completed work in the ai-agent-skills repository, a version-controlled project containing agent add-ons. It chooses between preparing a feature branch for review and publishing a version after changes are merged into the main branch.

Use it to update changelogs, README files, marketplace metadata, and version sections, then commit, push, create pull requests, or cut a release.

It gathers release tasks into one process so documentation, version information, commits, pushes, and pull requests are not forgotten. It also checks repository state and GitHub access before acting.

release — Skill for Claude Code by psenger

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 psenger/ai-agent-skills --skill release

Clone the repo

git clone --depth 1 https://github.com/psenger/ai-agent-skills

Made for: Claude Code.

Or install psenger-skills, the plugin that ships this one along with the rest of its 14 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/psenger/ai-agent-skills/release.svg)](https://agentmods.dev/skills/psenger/ai-agent-skills/release)

Your own site

<a href="https://agentmods.dev/skills/psenger/ai-agent-skills/release"><img src="https://agentmods.dev/badge/skills/psenger/ai-agent-skills/release.svg" alt="Measured on agentmods" height="20"></a>

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,910 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	$0.00139	$0.01910
Opus 5	$0.00069	$0.00955
Sonnet 5	$0.00028	$0.00382
Haiku 4.5	$0.00014	$0.00191

Measured 8d ago against content hash 40707a1269a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

release — 100% identical, 0 lines differ

.claude/skills/release/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Ships completed work. The skill detects context and runs the right phase:

On a feature branch with committed work → WRAP UP phase
On main after a merge → CUT RELEASE phase

For all message formatting, follow the conventions skill.

Step 0 — Auth & Identity (always)

Check for a GitHub MCP server in available tools. If none:

gh auth status

Stop if neither is available: "I need the GitHub MCP server or gh CLI authenticated. Run gh auth login."

Confirm identity — use mcp__github__get_me if the GitHub MCP server is available, otherwise:

gh api user --jq '"@\(.login) — \(.name)"'

Show the result and ask: "I'll be acting as @username — is that right?" Wait for confirmation.

WRAP UP Phase

Triggered when on any non-main branch (feature/, fix/, chore/, refactor/, test/, etc.) with a clean working tree.

Step 1 — Verify State

git branch --show-current     # must not be main
git status --porcelain        # must be empty — all work committed

If the tree is dirty, stop: "You have uncommitted changes. Commit or stash them first."

Step 2 — Detect What Changed

git diff main...HEAD --name-only

Determine:

Was a new skill added? Look for a new directory under skills/ not present on main.
Was an existing skill modified? Look for changes inside skills/<name>/.
Is this a bug fix, refactor, or docs change? Look at changed files outside skills/.

Derive the issue number from the branch name (e.g. feature/14-add-handoff-skill → #14). If none found, ask the user for the issue number.

Step 3 — Update Admin Files

CHANGELOG.md — add a bullet to ## [Unreleased] under the correct subsection:

New skill → ### Added
Updated skill → ### Changed
Bug fix → ### Fixed

Bullet format (see conventions skill):

- **skill-name** — <what changed and why>. ([#N](issue-url))

README.md — only if a new skill was added:

Add a row to the skills table
Add a ### skill-name prose section following the existing pattern

Read the full file on GitHub · 227 lines

Files

What ships with it

4 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.

8d ago First seen · 227 lines · 139 tokens per session scan A 40707a1269a3

Subscribe to this mod's changes

release is a skill published in the GitHub repository psenger/ai-agent-skills (10 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 1,910 once invoked, about $0.0007 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 2026-08-31.

Claude Code Git and workflow Releases agent-skills ai-agent claude codex developer-tools

release