release

release is a skill for Claude Code, Codex from vishalguptax/claude-code-manager. It costs 56 tokens per session (1,666 once invoked), scanned A, original, Apache-2.0.

A procedure for preparing a release of the Claude Manager VS Code extension. It reviews commits, writes release notes, updates the changelog, chooses a version change, and pushes the release commit.

In plain words
What is it for?
Use it when cutting or shipping a release, after checking the branch, tags, commits, and working tree.
Why use it?
It turns the changes since the previous version into the files and commit needed to start the publishing workflow.

Skill for Claude CodeCodex

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 skills/vishalguptax/claude-code-manager/release
Any agent
npx skills add vishalguptax/claude-code-manager --skill release
Clone the repo
git clone --depth 1 https://github.com/vishalguptax/claude-code-manager

Made for: Claude Code, Codex.

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 release

README.md
[![agentmods](https://agentmods.dev/badge/skills/vishalguptax/claude-code-manager/release.svg)](https://agentmods.dev/skills/vishalguptax/claude-code-manager/release)
Your own site
<a href="https://agentmods.dev/skills/vishalguptax/claude-code-manager/release"><img src="https://agentmods.dev/badge/skills/vishalguptax/claude-code-manager/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,666 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 $0.00056 $0.01666
Opus 5 $0.00028 $0.00833
Sonnet 5 $0.00011 $0.00333
Haiku 4.5 $0.00006 $0.00167

Measured 4d ago against content hash 5d73916529d2, 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 4d 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 · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Skill

Use this skill when the user says "release", "cut a release", "ship it", or similar.

This skill curates a release for the Claude Manager VS Code extension. The CI/CD workflow (.github/workflows/release.yml) handles the actual version bump, build, packaging, and publish to the Marketplaces — this skill just prepares human-readable release notes and decides the bump level via the commit message.


Flow

1. Verify git state

git status
git branch --show-current
  • Working tree must be clean (no uncommitted changes)
  • If not on main, ask the user whether to merge the current branch first
  • Check there's anything to release: git log $(git describe --tags --abbrev=0)..HEAD --oneline must be non-empty

If no commits since last tag, stop and tell the user there's nothing to release.

2. Gather commits since last release

LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [ -z "$LAST_TAG" ]; then
  git log --oneline
else
  git log $LAST_TAG..HEAD --oneline
fi

Read the list. Ignore commits authored by github-actions[bot] (those are auto-bumps).

3. Categorize commits

Group commits by conventional-commit prefix:

Prefix Section title
feat: / feature: Features
fix: Bug Fixes
perf: Performance
refactor: Refactoring
docs: Documentation
style: UI/Styling
test: Tests
build: / chore: / ci: Build / CI
anything else Other

Skip commits that are purely version bumps (release: v1.2.3) or merge commits (Merge branch) unless they carry meaningful content.

4. Decide bump level

Inspect commit messages to determine patch / minor / major:

  • Major: any commit message contains [major] or starts with breaking: or BREAKING CHANGE
  • Minor: any commit message contains [minor] or starts with feat: or feature:
  • Patch: anything else (fixes, chores, docs, perf, refactor, style)

Read the full file on GitHub · 208 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. 4d ago First seen · 208 lines · 56 tokens per session scan A 5d73916529d2

Subscribe to this mod's changes

release is a skill published in the GitHub repository vishalguptax/claude-code-manager (28 stars, last pushed 25d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,666 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.