Agent Claude Code
Executes the plan literally. Uses a light model — the plan must be straightforward and unambiguous.
Agent Claude Code
Executes the plan literally. Uses a light model — the plan must be straightforward and unambiguous.
Agent Claude Code
Plan Clarity Reviewer reads a plan file and assesses its clarity.
Agent Claude Code
Reviews the plan implementation across six dimensions — Architecture, Maintainability, Performance, Security, Completeness, and Bug Hunt — then produces a priority sorted report.
Command Claude Code
Review the implementation of the plan.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing inject-base-rules.py. From semihkayan/codeweave-mcp.
Hook Claude Code
Runs before the agent uses a tool for Agent and ExitPlanMode tool calls, executing inject-rules-into-subagent.py and plan-review-gate.py (2 commands). From semihkayan/codeweave-mcp.
Hook Claude Code
Runs after a tool call finishes for ExitPlanMode and EnterPlanMode tool calls, executing implementation-router.py and init-plan-mode.py (2 commands). From semihkayan/codeweave-mcp.
Settings file Claude Code
Agent settings declaring 3 hook events (UserPromptSubmit, PreToolUse, PostToolUse).
Skill Claude CodeCodex
Test codeweave-mcp tools against any project using TestHarness. Use this whenever verifying tool behavior, testing a code change, or running custom assertions — e.g. "test the harness", "run tests against X project", "does semanticsearch work correctly".
MCP server Claude CodeCodexCursor +2
MCP server "codeweave" as configured in semihkayan/codeweave-mcp. Launched with /opt/homebrew/Cellar/node@22/22.22.2/bin/node /opt/homebrew/lib/node_modules/@co.
Instructions file
Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.