5 tagged interpretable context methodology, measured the same way as everything else here.
Browse within: agent-architecture 5claude-plugin 5icm 5spec-driven-development 5
Hook
Runs to expand your prompt before the agent sees it, executing gate_implement.py and gate_clarification.py via uv with --no-project and --script (2 commands). From andyrids/icm-spec.
Hook
Runs before the agent uses a tool for Edit and Write tool calls, executing gate_spec_edit.py and gate_output_naming.py via uv with --no-project and --script (4 commands). From andyrids/icm-spec.
Hook
Runs after a tool call finishes for Edit and Write tool calls, executing gate_plan_frontmatter.py and gate_spec_frontmatter.py via uv with --no-project and --script (4 commands). From andyrids/icm-spec.