The Codebase Intelligence layer for AI coding agents. Semantic indexing, graph navigation, and repository intelligence
This repository also configures its own agents. See what TeaRAGs-MCP tells them →
Hook Claude Code
One of 5 in hooks.json
Runs when a session starts, executing session-start.sh, session-codex-rules.sh, session-digest.sh and reread-ledger.mjs with --harness (4 commands). From artk0de/TeaRAGs-MCP.
Hook Claude Code
One of 5 in hooks.json
Runs when a subagent starts, executing subagent-block.sh. From artk0de/TeaRAGs-MCP.
Hook Claude Code
One of 5 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing turn-routing.sh, search-drift.sh and reread-ledger.mjs with --harness (3 commands). From artk0de/TeaRAGs-MCP.
Hook Claude Code
One of 5 in hooks.json
Runs before the agent uses a tool for ^(Bash, shell and exec_command)$ tool calls, executing one-file-read.sh, search-drift.sh and reread-ledger.mjs with --harness (3 commands). From artk0de/TeaRAGs-MCP.
Hook Claude Code
One of 5 in hooks.json
Runs after a tool call finishes for ^mcp__.*tea[-_]rags.*__, ^(Bash, shell and exec_command)$ tool calls, executing search-drift.sh and reread-ledger.mjs with --harness (3 commands). From artk0de/TeaRAGs-MCP.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: