Give Claude Code a persistent mind: an autonomous agent framework that sets its own goals, forms predictions, and learns from outcomes across sessions.
Hook Claude Code
Runs before the agent uses a tool for Read, Skill, Bash, ScheduleWakeup, Write, Edit and MultiEdit tool calls, executing context-reads-gate.sh, task-output-read-advisory.sh, context-reads-skill-gate.sh, utilization-gate.sh, bash-agent-inject.sh, bash-path-resolution-hook.sh, bare-bash-authoring-gate.sh…
Hook Claude Code
Runs after a tool call finishes for Read, Write, Edit, MultiEdit and Bash tool calls, executing context-reads-record.sh, tree-write-fence.sh, context-reads-invalidate.sh, tree-sync-check.sh, skill-stdin-json-lint.sh, lock-symmetry-lint.sh, evolution-record.sh, owncloud-push-on-write.sh, iteration-close-reminder.sh…
Hook Claude Code
Runs before the context is compacted for auto tool calls, executing precompact-serialize.sh and precompact-checkpoint.sh via bash (2 commands). From zkysar1/Claude-Mind.
Hook Claude Code
Runs when a session starts, executing sessionstart-orchestrator.sh via bash. From zkysar1/Claude-Mind.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing user-prompt-retrieval-inject.sh via bash. From zkysar1/Claude-Mind.
Hook Claude Code
Runs to expand your prompt before the agent sees it, executing user-prompt-skill-record.sh via bash. From zkysar1/Claude-Mind.
Hook Claude Code
Runs when the agent finishes a response, executing stop-hook.sh via bash. From zkysar1/Claude-Mind.
Hook Claude Code
Runs on the StopFailure event, executing stop-failure-hook.sh via bash. From zkysar1/Claude-Mind.