A discipline layer for Claude Code. Hooks at every tool boundary, a workflow that runs from intake to commit, and a small constitution the agent cannot bypass.
Hook Claude Code
Runs before the agent uses a tool for AskUserQuestion, Bash, Write, Edit, MultiEdit, NotebookEdit and Write tool calls, executing notify.mjs, destructive_cmd_guard.mjs, state_write_guard.mjs, git_commit_guard.mjs, gitignore_leak_guard.mjs, process_lifecycle_guard.mjs, setup_guard.mjs, env_guard.mjs…
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing consent_gate_grant.mjs via node. From friedbotstudio/baseline.
Hook Claude Code
Runs after a tool call finishes for Write, Edit, MultiEdit and Bash tool calls, executing lint_runner.mjs, test_runner.mjs and phase_timer.mjs via node (4 commands). From friedbotstudio/baseline.
Hook Claude Code
Runs when a session starts, executing memory_session_start.mjs via node. From friedbotstudio/baseline.
Hook Claude Code
Runs when the agent finishes a response, executing memory_stop.mjs, harness_continuation.mjs and notify.mjs via node (3 commands). From friedbotstudio/baseline.
Hook Claude Code
Runs when the agent sends a notification for permission_prompt and idle_prompt tool calls, executing notify.mjs via node (2 commands). From friedbotstudio/baseline.
Hook Claude Code
Runs before the context is compacted for manual and auto tool calls, executing memory_pre_compact.mjs via node. From friedbotstudio/baseline.