Skip to main content
skill CX Codex

release-guard — Claude Code skill: release checks before merge

release-guard is a Claude Code skill that checks a repository before merge or release, comparing documented commands with package.json and architecture notes with current code paths.

MIT ★ 1,198 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill release-guard -a claude-code
Open on GitHub

What release-guard does

Point it at the repo before a merge or a release and you get a pass/fail report with file references you can open. It starts by matching the commands written in the docs to the ones package.json defines. From there it compares the architecture write-up with the paths the code uses today, and confirms the safety controls are still written down and still enforced.

The focus areas come from Claude-Code-Agent-Monitor itself: how hooks flow and what happens when one fails, the lifecycle rules for sessions and agents, the MCP safety gates and the host setup steps, and whether the troubleshooting section still tells the truth. On a project with no hooks or MCP wiring, several of those items have nothing to attach to.

A checklist ships with the skill at references/release-checklist.md, and the run follows it. For Claude the file lands in ~/.claude/skills/release-guard/SKILL.md; for Codex it goes to .agents/skills/release-guard/SKILL.md.

What it helps with

  • match documented commands against package.json before a merge
  • catch architecture docs that drifted from real code paths
  • confirm the safety controls are still documented and on
  • get a pass/fail report with file references instead of vague notes
  • walk the hook and session-lifecycle items

Example prompts for the agent

  • Run release-guard on this repo and give me the pass/fail report with file references.
  • Use the release-guard skill to check whether the docs commands match package.json.
  • Go through references/release-checklist.md and tell me where the architecture docs and the code disagree.

How to install release-guard

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill release-guard -a claude-code

2Manually: put the files in place

~/.claude/skills/release-guard/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/release-guard/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about release-guard

How do I install release-guard in Claude Code?

Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill release-guard -a claude-code. The skill file ends up at ~/.claude/skills/release-guard/SKILL.md.

What does release-guard do?

It compares the docs and scripts with what the repo actually contains: commands against package.json, the architecture write-up against code paths, the safety controls against what is enabled. Each item comes back as pass or fail with a file reference.

Where does the checklist live?

Inside the skill, at references/release-checklist.md. The run follows that file.

Source text

SKILL.md · MIT
---
name: release-guard
description: Run release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.
---

# Release Guard Skill

## Workflow
- Check command consistency across docs and `package.json`.
- Verify architecture docs align with current code paths.
- Validate that safety controls are still documented and enforced.
- Report pass/fail with concrete file references.

## Focus areas
- Hook flow and failure behavior.
- Session/agent lifecycle semantics.
- MCP safety gates and host setup instructions.
- Troubleshooting accuracy.

## References
- `references/release-checklist.md`

© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set155

The whole set →
run-operator run-operator — a subagent for operating Claude Code and Codex processes through CCAM, with a parameter check before each run, message, or stop action. CX Codex ★ 1,198repo stars mcp-reviewer mcp-reviewer reviews MCP server changes: tool schemas, safety gates on destructive calls, error handling and stdio correctness. Useful before you merge work on a server. CX Codex ★ 1,198repo stars backend-node backend-node is a Claude Code rule for Node.js backend files and hook ingestion logic. It keeps API responses compatible and enforces database transaction safety. CX Codex +1 ★ 1,198repo stars report report is a Claude Code command that creates CCAM executive, cost, reliability, or workflow reports. Specify a report type and data scope in the request. CX Codex +1 ★ 1,198repo stars repo-onboarding repo-onboarding guides AI coding agents through codebase architecture, layer selection, and test command discovery before editing. CX Codex +1 ★ 1,198repo stars mcp-maintainer The mcp-maintainer skill guides maintenance of the repository’s local MCP server, from checking its API to validating tool changes. Use it when updating MCP tools or investigating runtime issues. CX Codex +1 ★ 1,198repo stars file-headers file-headers makes each source file open with a short, honest overview plus the exact line @author Son Nguyen <[email protected]>. CX Codex +1 ★ 1,198repo stars status Polls the local Claude Code Agent Monitor dashboard to print health status and session counts in a single line. CX Codex +1 ★ 1,198repo stars

Project sponsors

Companies that keep this analytics open