
Release Guard
This is a pre-merge sanity check that walks through your repository looking for drift between what your docs promise and what your code actually does. It cross-references commands in documentation against package.json, validates that architecture docs still match current code paths, and confirms safety controls are both documented and enforced. The skill focuses on hook behavior, session lifecycle, MCP safety gates, and troubleshooting accuracy, then gives you a pass/fail with file references. It's useful right before cutting a release when you need to catch the quiet inconsistencies that accumulate between launches. Assumes you have a release checklist doc to work from.
- GitHub stars
- 455
- last updated
- Jun 11, 2026
Install
$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill release-guard --agent claude-codeInstalls into .claude/skills of the current project.
Files
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
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Details
- Repository
- github.com/hoangsonww/claude-code-agent-monitor
- Categories
- Testing & QA, DevOps & CI/CD, Git & Pull Requests, Documentation, AI & Agent Building, Release Management
- License
- MIT
- First seen
- Jun 11, 2026
More from hoangsonww/claude-code-agent-monitor
All 24- Repo Onboarding
- Session Compare
- Session Debug
- Session Report
- Ship Feature
- Sprint Summary
- Usage Trends
- Weekly Report
- Workflow Optimizer
- Anomaly Alert
- Cost Breakdown
- Daily Standup
- Dashboard Status
- Data Export
- Debug Live Issue
- Health Check
- Hook Diagnostics
- Mcp Maintainer
- Mcp Operations
- Optimization Suggest
- Pattern Detect
- Productivity Score
- Quick Stats
Recommended
More Testing & QA1
Home Assistant Integration knowledgehome-assistant/coreEverything you need to know to build, test and review Home Assistant Integrations. If you're looking at an integration, you must use this as your primary refere0skills.sh installs
2
meta-adshoodini/ai-agents-skillsPull, analyze, manage, and CREATE Meta ads (Facebook, Instagram, Messenger, Threads, Click-to-WhatsApp) via the Marketing API. Use when the user mentions Meta/F0skills.sh installs
3
active-directory-attackhypnguyen1209/offensive-claudeActive Directory penetration testing — BloodHound enumeration, Kerberos attacks (Kerberoasting, AS-REP, Golden/Silver Ticket), NTLM relay, DCSync, lateral movem0skills.sh installs
4
cloud-securityhypnguyen1209/offensive-claudeCloud penetration testing — AWS/Azure/GCP privilege escalation, container escape, Kubernetes attacks, serverless exploitation, IaC misconfigurations0skills.sh installs
5
mobile-pentesthypnguyen1209/offensive-claudeMobile application penetration testing — Android/iOS static/dynamic analysis, Frida instrumentation, SSL pinning bypass, root/jailbreak detection bypass, deep-l0skills.sh installs
6
network-attackhypnguyen1209/offensive-claudeNetwork penetration testing — lateral movement, pivoting, protocol attacks, traffic interception, Active Directory exploitation, wireless attacks0skills.sh installs