Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Runs before the agent uses a tool for Read, Edit, Write, Read, Grep, Task and Edit tool calls, executing pre-tool-use-broadcast.mjs, path-rules.mjs, tldr-read-enforcer.mjs, smart-search-router.mjs, tldr-context-inject.mjs, arch-context-inject.mjs, file-claims.mjs, edit-context-inject.mjs and signature-helper.mjs via…
Runs when a session starts on resume, compact, clear, startup and resume, executing persist-project-dir.sh, session_start.sh, session-register.mjs, hook_launcher.py, session-start-continuity.mjs and session-start-tldr-cache.mjs via bash (6 commands). From parcadei/Continuous-Claude-v3.
Runs when you submit a prompt, before the agent sees it, executing skill-activation-prompt.mjs, hook_launcher.py, memory-awareness.mjs, impact-refactor.mjs and user_prompt_submit.sh via node (5 commands). From parcadei/Continuous-Claude-v3.
Runs when the agent finishes a response, executing hook_launcher.py, stop_hook.sh and compiler-in-the-loop-stop.mjs via uv (3 commands). From parcadei/Continuous-Claude-v3.
Runs when a session ends, executing session-end-cleanup.mjs, session-outcome.mjs and session_end.sh via node (3 commands). From parcadei/Continuous-Claude-v3.
3.9k▲
+2 7mo agoA
tokens not measured
originalMIT
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: