Runs an autonomous agent loop that repeats a task with self-correction, task tracking and live monitoring, so a coding assistant keeps working until the job is finished. Works with Claude Code, OpenCode, Codex and GitHub Copilot.
@th0rgalSkills for orchestrating AI agents on long-running coding work in isolated workspaces. They cover splitting work across parallel workers, advising a stuck executor, and monitoring multi-day missions with model switching.
@th0rgalWhen and how a mission should rent boat.dev managed VMs: whether to use one at all, size choice, one warm snapshot per project,…
@th0rgalAutonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive…
@th0rgalHow Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch…
@th0rgalUse this skill whenever a user wants to run, install, configure, or understand open-ralph-wiggum (ralph). This skill can be used…
@th0rgalPersistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely…
@th0rgalBoss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do…
@th0rgalExecutor skill: do the work yourself, and consult a single persistent smart-model advisor via ask_worker when you hit a dead end.
@th0rgalWorker skill for boss-spawned missions. Stay within scope, verify, and report blockers quickly.
@th0rgalSteer sandboxed.sh projects, roadmaps, decisions from chat.
@th0rgalDelegate coding/automation tasks to sandboxed.sh missions via the mcp_sandboxed_assistant_* MCP. Each mission runs in an isolated…
@th0rgalIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
