deploy-check
[experimental] Evaluate deployment risk by analyzing code changes against incident history, active incidents, and on-call readiness. Forked-subagent flow may not have MCP access in all Claude Code contexts.
Install
With your agent
Install OMGSkills skill "rootly-ai-labs/rootly-claude-plugin:skills/deploy-check" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/Rootly-AI-Labs/rootly-claude-plugin /tmp/rootly-claude-plugin && ln -s /tmp/rootly-claude-plugin/skills/deploy-check ~/.claude/skills/deploy-checkFrom README
Pre-Deploy Safety Check (experimental) Experimental: this skill uses context: fork to delegate to the deploy-guardian agent. In some Claude Code contexts the forked subagent does not inherit the plugin's MCP tools. If the agent reports MCP tools unavailable, run /rootly:status to manually check active incidents before deploying. You are evaluating whether it is safe to deploy the current code changes. Follow this workflow carefully. Current changes !git diff --stat HEAD Current branch !git branch --show-current Recent commits !git log --oneline -5 Workflow Assess Changes Review the git diff output above. If the diff is empty (no changes), report "No changes to evaluate -- working tree is clean" and stop. Identify which files and components are affected by the changes.