Plan-then-build AI coding for Claude Code & Codex CLI — you approve the plan before the model writes a line of code. SPEC → PLAN → TEST → CODE → REVIEW → LEARN
Hook Claude Code
Runs when a session starts on compact, executing post-compact-context.py, map-memory-finalize.py and map-memory-recall.py (3 commands). From azalio/map-framework.
Hook Claude Code
Runs when a session ends, executing map-memory-endmark.py. From azalio/map-framework.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write, Read, MultiEdit, Bash, Edit, Write, MultiEdit, Edit, Write, MultiEdit and Bash tool calls, executing safety-guardrails.py, workflow-gate.py and workflow-context-injector.py (3 commands). From azalio/map-framework.
Hook Claude Code
Runs after a tool call finishes for Edit, Write, MultiEdit and Bash tool calls, executing ralph-iteration-logger.py. From azalio/map-framework.
Hook Claude Code
Runs before the context is compacted, executing ralph-context-pruner.py and pre-compact-save-transcript.py (2 commands). From azalio/map-framework.
Hook Claude Code
Runs when a subagent finishes, executing map-token-meter.py. From azalio/map-framework.
Hook Claude Code
Runs when the agent finishes a response, executing scrub-internal-ids.py, end-of-turn.sh, map-token-meter.py and map-memory-capture.py (4 commands). From azalio/map-framework.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing detect-clarification-triggers.py, context-meter.py and map-memory-recall.py (3 commands). From azalio/map-framework.