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.
npx agentmods add commands/paulpreibisch/agentvibes/prepare-releasegit clone --depth 1 https://github.com/paulpreibisch/AgentVibesWrote 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.
[](https://agentmods.dev/commands/paulpreibisch/agentvibes/prepare-release)<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/prepare-release"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/prepare-release.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00008 | $0.00776 |
| Opus 5 | $0.00004 | $0.00388 |
| Sonnet 5 | $0.00002 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
prepare-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prepare-release
Prepares a new AgentVibes release with AI-generated release notes.
This command:
- Runs full test suite - MUST pass before proceeding ✅
- Validates Sonar quality gates - MUST pass before proceeding ✅
- Analyzes all changes since the last release
- Generates an intelligent summary using Claude AI
- Creates/updates RELEASE_NOTES.md
- Bumps the version
- Commits everything
- Ready for you to push
Usage
# Patch release (bug fixes)
/prepare-release patch
# Minor release (new features)
/prepare-release minor
# Major release (breaking changes)
/prepare-release major
What Gets Generated
- AI Summary: High-level overview of changes
- Categorized Changes: Features, fixes, docs, tests
- User Impact: What users should know
- Migration Notes: If breaking changes exist
Example Output
# Release v1.0.10
## AI Summary
This release focuses on improving test reliability and fixing directory
detection issues. The test suite now properly handles bash warnings and
all 27 tests pass consistently across different environments.
## Changes
### 🐛 Bug Fixes
- Fixed test path resolution for BATS tests
- Updated test assertions to handle bash warnings
### 🧪 Testing
- Added comprehensive test coverage for replay command
- All tests now passing in CI/CD
## User Impact
- More reliable installation and testing
- Better error messages
- No breaking changes
Implementation
When executing this command, Claude MUST follow these steps in order:
-
Run Test Suite (MANDATORY FIRST STEP):
- Execute
npm test(which runs syntax validation, BATS tests, and coverage tests) - If ANY tests fail, STOP immediately and report the failures
- Do NOT proceed with any release operations if tests fail
- Example output: "🧪 Running tests... ✅ All 213 BATS tests passed, ✅ All 38 Node tests passed"
- Execute
-
Validate Sonar Quality Gates (MANDATORY SECOND STEP):
- Check all bash scripts for
set -euo pipefail(strict mode) - Verify no hardcoded credentials in code
- Validate proper variable quoting in bash scripts
- Check for input validation and error handling
- Review any new or modified files for security issues
- If ANY quality gate fails, STOP immediately and report the issues
- Example output: "🛡️ Validating quality gates... ✅ All Sonar requirements met"
- Note: Document any known minor issues (like missing strict mode in legacy scripts) if they existed before this release
- Check all bash scripts for
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.
- yesterday First seen · 99 lines · 8 tokens per session scan A cf9a2ccf18d0
prepare-release is a command published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 776 once invoked, about $0.0000 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.
Other commands, from other repositories
rollback
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
release-notes
Curate a CHANGELOG.md entry from commits since the last release; with a bump arg, also version, commit, and push the tag — then hand the npm publish to the user (they publish manually). nightly instead cuts a pre-release from the nightly branch. Also flags when the separately-published provider SDK needs a republish.
release-prep
Automated release readiness validation.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.