release

release is a command for Claude Code from paulpreibisch/AgentVibes. It costs 16 tokens per session (3,130 once invoked), scanned A, original, Apache-2.0.

A release command that tests a project, prepares release notes, updates version information, and publishes a new release after human review.

In plain words
What is it for?
Use it to create GitHub and npm releases, update project documentation, commit changes, and push version tags.
Why use it?
It groups the many release steps into one guided process and stops when tests fail or review is needed.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md.

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 commands/paulpreibisch/agentvibes/release
Clone the repo
git clone --depth 1 https://github.com/paulpreibisch/AgentVibes

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 release

README.md
[![agentmods](https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/release.svg)](https://agentmods.dev/commands/paulpreibisch/agentvibes/release)
Your own site
<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/release"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,130 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 $0.00016 $0.03130
Opus 5 $0.00008 $0.01565
Sonnet 5 $0.00003 $0.00626
Haiku 4.5 $0.00002 $0.00313

Measured 3d ago against content hash 1b29dc1c72c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 3d 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/commands/release.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/release

Semi-automated release process with AI-generated release notes and human approval checkpoints.

This command:

  1. Runs full test suite - MUST pass before proceeding ✅
  2. Validates Sonar quality gates - MUST pass before proceeding ✅
  3. Analyzes all changes since the last release (git log + diffs)
  4. Reads actual code changes to understand context
  5. Generates AI summary and release notes
  6. PAUSES for human review of RELEASE_NOTES.md ⏸️
  7. PAUSES for human review of AI summary ⏸️
  8. Updates installer.js and update scripts with AI summary
  9. Updates README.md with new version and release info ⚠️
  10. Bumps the version using npm version
  11. Commits everything together (including updated README)
  12. Pushes to master with --follow-tags
  13. Creates GitHub release
  14. Publishes to npm (packages README at this moment!)

⚠️ CRITICAL ORDER: README must be updated (step 8) BEFORE npm publish (step 13) because npm packages whatever README exists at publish time. This ensures the npm package page displays current release info.

🧪 TEST REQUIREMENT: The test suite MUST pass before any release operations begin. If tests fail, the release is aborted immediately. This prevents publishing broken code to npm.

🛡️ SONAR QUALITY GATES: All SonarCloud quality requirements from CLAUDE.md MUST be validated before release:

Shell Script Security (Bash)

  • ✅ All bash scripts MUST have set -euo pipefail at the top (strict mode)
  • ✅ All variables MUST be quoted (e.g., "$VARIABLE", not $VARIABLE)
  • ✅ No hardcoded credentials (API keys, passwords, tokens)
  • ✅ Input validation for all external inputs
  • ✅ Secure temp directories ($XDG_RUNTIME_DIR with fallback)
  • ✅ Path traversal prevention
  • ✅ File ownership verification before processing
  • ✅ Single quotes in trap statements (deferred expansion)

JavaScript/Node.js Security

  • ✅ Use path.resolve() for path operations
  • ✅ Path safety validation (prevent traversal)
  • ✅ No sensitive data in logs (mask credentials)
  • ✅ Try-finally for resource cleanup

Read the full file on GitHub · 342 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. 3d ago First seen · 342 lines · 16 tokens per session scan A 1b29dc1c72c8

Subscribe to this mod's changes

release is a command published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 3,130 once invoked, about $0.0001 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 2026-09-03.