PreToolUse
01Hook
Runs before the agent uses a tool for Edit, Write, MultiEdit, Bash and ExitPlanMode tool calls, executing pre-edit-guard.sh, pre-bash-guard.sh and pre-exitplan-guard.sh via bash (3 commands). From iroha924/mumei.
Your build is green — but did the agent make it green by weakening the tests? mumei re-runs them from a clean HEAD, freezes what must not be tuned, and reads the diff for deleted tests and suppressed errors. Enforced in Hooks, not asked for in a prompt.
Hook
Runs before the agent uses a tool for Edit, Write, MultiEdit, Bash and ExitPlanMode tool calls, executing pre-edit-guard.sh, pre-bash-guard.sh and pre-exitplan-guard.sh via bash (3 commands). From iroha924/mumei.
Hook
Runs on the TaskCreated event, executing post-task-event.sh via bash. From iroha924/mumei.
Hook
Runs when a task is marked completed, executing post-task-event.sh via bash. From iroha924/mumei.
Hook
Runs after a tool call finishes for Edit, Write, MultiEdit and Bash tool calls, executing post-edit-guard.sh, lint-tasks.sh and post-bash-guard.sh via bash (3 commands). From iroha924/mumei.
Hook
Runs when the agent finishes a response, executing stop-guard.sh and stop-cost-backfill.sh via bash (2 commands). From iroha924/mumei.
Hook
Runs when you submit a prompt, before the agent sees it, executing userprompt-context-hint.sh via bash. From iroha924/mumei.
Hook
Runs before the context is compacted for manual and auto tool calls, executing pre-compact-state-dump.sh via bash. From iroha924/mumei.
Hook
Runs when a session starts on startup, resume, startup and resume, executing session-start-status.sh and session-start-bypass-notice.sh via bash (2 commands). From iroha924/mumei.
Hook
Runs after the context is compacted for manual and auto tool calls, executing post-compact-validate.sh via bash. From iroha924/mumei.
Hook
Runs on the FileChanged event for requirements.md, tasks.md and state.json tool calls, executing file-changed-validate.sh via bash. From iroha924/mumei.
Hook
Runs on the CwdChanged event, executing cwd-changed-detect.sh via bash. From iroha924/mumei.
Hook
Runs after instructions files are loaded for session_start and compact tool calls, executing instructions-loaded-audit.sh via bash. From iroha924/mumei.
Hook
Runs to expand your prompt before the agent sees it for ^mumei:shelve$ tool calls, executing userprompt-expansion-context.sh via bash. From iroha924/mumei.
Hook
Runs on the ConfigChange event for user_settings, project_settings, local_settings, policy_settings and skills tool calls, executing config-change-audit.sh via bash. From iroha924/mumei.
Hook
Runs when a session ends, executing session-end-audit.sh via bash. From iroha924/mumei.
Hook
Runs when a tool call fails for Bash, Edit, Write and MultiEdit tool calls, executing post-tool-failure-audit.sh via bash. From iroha924/mumei.
Hook
Runs when a subagent starts for ^(mumei:)?(adversarial-reviewer, design-reviewer, requirements-reviewer, security-reviewer, spec-compliance-reviewer, tasks-reviewer, issue-validator and memory-curator)$ tool calls, executing subagent-cost-log-start.sh and subagent-context-inject.sh via bash (2 commands). From…
Hook
Runs when a subagent finishes for ^(mumei:)?(adversarial-reviewer, design-reviewer, requirements-reviewer, security-reviewer, spec-compliance-reviewer, tasks-reviewer, issue-validator and memory-curator)$ tool calls, executing subagent-cost-log.sh via bash. From iroha924/mumei.