capitalthought

Multipov Reliability — AI skill for Claude Code

AI community

Run a multi-agent reliability-focused code review on $ARGUMENTS (default: current branch changes) via the multipov.ai MCP server.

How to install Multipov Reliability

Installs to ~/.claude/skills/capitalthought-multipov-docs-multipov-reliability/SKILL.md

Terminal

mkdir -p ~/.claude/skills/capitalthought-multipov-docs-multipov-reliability && curl -fsSL https://raw.githubusercontent.com/capitalthought/multipov-docs/HEAD/skills/multipov-reliability.md -o ~/.claude/skills/capitalthought-multipov-docs-multipov-reliability/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Multipov Reliability does

Run a multi-agent **reliability-focused** code review on `$ARGUMENTS` (default: current branch changes) via the multipov.ai MCP server. Same panel shape and input handling as `/multipov-code`, but steered toward uptime, maintainability, logging, observability, and failure recovery via `custom_instructions`.

Determine the diff range from arguments: `--staged`, `--unstaged`, or a ref range like `main..HEAD` (default).

Fallback: Review Last Committed Work

Before proceeding, check whether the

Alternatives in AI

Room — Open-source earning-focused swarm intelligence engine 838 ★
Metaharness — 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MC 616 ★
Rmslop — Remove AI code slop from current branch 508 ★