These loadouts are about how agents use Git when work is shared. One gives every agent its own worktree and branch; another keeps commits small and pull requests reviewable, with a leak check before pushing. A handoff loadout records the commit a HANDOFF.md was written at and flags it once HEAD moves on, a guarded loop uses commits to measure progress, and the extension-vetting loadout proves a checkout matches its pinned SHA.
Every one installs for Claude Code, Codex CLI, Cursor, Gemini CLI, Antigravity CLI and GitHub Copilot unless its card says otherwise.
Run an agent in a Ralph-style loop with guard rails: a fresh process per pass, state in files, iteration and no-progress limits, and a check it cannot fake.
Write HANDOFF.md before you clear context or switch agents: goal, decisions, exact failing test, next step, commit. A checker flags stale or incomplete handoffs.
Rules and two skills for running several coding agents at once, one task per git worktree: isolation, ports, dependencies, rebasing and clean-up.
Commit and PR rules for coding agents: small PRs, a four-part body, screenshots with gh --attach and a leak check for session links and secrets before pushing.
Treat agent skills, plugins and MCP servers as dependencies: pin by SHA or exact version, prove HEAD matches the pin, scan every file, and get a human yes.
Looking for something narrower? Search within Git or filter everything.