Skill Claude CodeCodex
Each autopilot invocation reads state, does ONE unit of work, exits. The caller re-invokes. This preserves fresh context at every level — including during the ralph loop.
Skill Claude CodeCodex
Socratic reqs interview; clarify vague/ambiguous goals.
Skill Claude CodeCodex
"comprehensive research", "investigate X", "what's known about Y".
Skill Claude CodeCodex
Drive an omh-ralph run: dispatch, evidence, commit hygiene.
Skill Claude CodeCodex
Execute one omh-ralph task: file-scope, commit, report.
Skill Claude CodeCodex
Each ralph invocation does ONE unit of work and exits. The caller re-invokes for the next task. This eliminates context window exhaustion and makes every invocation a clean checkpoint.
Skill Claude CodeCodex
Drive omh-ralplan: context package, rounds, distillation.
Skill Claude CodeCodex
Planner+Architect+Critic→consensus impl plan (≤3 rounds).
Skill Claude CodeCodex
Drive omh-triage: when to invoke, how to run rounds.
Skill Claude CodeCodex
Multi-role consensus triage of an issue backlog.
Skill Claude CodeCodex
Ad-hoc verification tempfile pattern for executor turns that trigger 'Verification status: unverified'.
Skill Claude CodeCodex
Saturate loop kind taxonomy: six typed loop kinds, per-kind specs, turn results, terminal states. OMH v18 skill→kind mapping.
Plugin Claude Code
Bundles 18 commands · 129 tokens together
Agent-maintained Zettelkasten knowledge graph.
Plugin Claude Code
Access Telegram conversations, channels, and Saved Messages via natural language queries.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: