What ouroboros runs automatically, and when. A hook is a command Claude Code fires at a fixed moment, without you asking for it.
Claude Code
> /plugin marketplace add Q00/ouroboros> /plugin install ouroboros@ouroboros
Cursor
Cursor also runs Claude Code hooks from .claude/settings.json, so copy these hooks there to use them in Cursor.
What fires, and when
SessionStart
Fires once when a session begins, and again after a context compaction. It is where a plugin sets up its environment, or restores state the compaction dropped.
*ROOT="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"; if [ -z "$ROOT" ]; then printf '%s\n' 'Ouroboros hook skipped: plugin root is unavailable.' >&2; exit 0; fi; SCRIPT="$ROOT/scripts/session-start.py"; if [ ! -r "$SCRIPT" ]; then printf '%s\n' "Ouroboros hook skipped: $SCRIPT is unavailable." >&2; exit UserPromptSubmit
Fires before Claude sees each prompt you send. A plugin can use it to inject context, so the same instruction reaches the model every turn instead of only at session start.
*ROOT="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"; if [ -z "$ROOT" ]; then printf '%s\n' 'Ouroboros hook skipped: plugin root is unavailable.' >&2; exit 0; fi; SCRIPT="$ROOT/scripts/keyword-detector.py"; if [ ! -r "$SCRIPT" ]; then printf '%s\n' "Ouroboros hook skipped: $SCRIPT is unavailable." >&2; exPostToolUse
Write|EditROOT="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"; if [ -z "$ROOT" ]; then printf '%s\n' 'Ouroboros hook skipped: plugin root is unavailable.' >&2; exit 0; fi; SCRIPT="$ROOT/scripts/drift-monitor.py"; if [ ! -r "$SCRIPT" ]; then printf '%s\n' "Ouroboros hook skipped: $SCRIPT is unavailable." >&2; exit 
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Stars on GitHub
Splits a complex task across several specialized Claude Code agents working in parallel, then keeps going until the result is checked. You describe what you want in plain language instead of memorizing commands.
@yeachan-heoA plugin that runs coding tasks through multiple AI backends (Codex, Claude, Gemini, OpenCode) with a structured development workflow, parallel execution, browser automation and multi-session task checkpointing.
@stellarlinkcoCoordinates AI agents with mechanical protocol enforcement, a workflow gate, memory validation and a session hook. Includes a catalog of specialist agents and has no runtime dependencies.
@gammalabtechnologiesBernstein is a Claude Code plugin for orchestrating AI agents. It adds skills to list and inspect agents, review and approve tasks, create tasks, track costs and budgets, and show alerts for failed or stalled work.
@sipyourdrink-ltdA Claude Code plugin that enforces finishing multi-step tasks with evidence and verification at each stage. It works as a procedure for Opus or any Claude model, not as chance.
@fivetakuAdjusts how third-party models behave inside Claude Code so they run closer to a native Opus session, covering subagent lifecycle, session hooks and tool interception. It does not replace your gateway, provider mapping or account setup.
@hellowind777Runs a PDCA workflow with phase gating, spec checks, and delegation to sub-agents for planning, QA, and deployment. Fires at session start and on prompts, edits, task creation, and phase transitions.
@ww-w-aiFusion-Fable is a Claude Code plugin that answers hard questions by sending them to a panel of models working in parallel, then having a judge model combine their answers. It also includes a planning skill that runs an OMC requirements interview before producing an implementation plan.
@duolahypercho