PreCompact
217Hook Claude Code
Runs before the context is compacted for manual and auto tool calls, running an inline shell check (2 commands). From Soulcynics404/AgentForge.
270 tagged LLM, measured the same way as everything else here.
Browse within: claude-code-plugin 47Multi-Agent 35agent-memory 35knowledge-graph 35model-context-protocol 35context-management 23local-first 23knowledge-base 22ai-memory 21embeddings 20markdown 18coding-agents 14sqlite 14long-term-memory 13
Hook Claude Code
Runs before the context is compacted for manual and auto tool calls, running an inline shell check (2 commands). From Soulcynics404/AgentForge.
Hook
Runs when a session starts on startup, resume, clear and compact, executing session-start.mjs via node. From hj1105/kontext-brain-ts.
Hook
Runs before the agent uses a tool for ^apply_patch$ tool calls, executing server.mjs via node with --authorize-write-hook. From hj1105/kontext-brain-ts.
Hook
Runs after a tool call finishes for ^(apply_patch and Bash)$ tool calls, executing server.mjs via node with --observe-write-hook. From hj1105/kontext-brain-ts.
Hook
Runs when a session starts, running an inline shell check. From epicsagas/epic-harness.
Hook
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From epicsagas/epic-harness.
Hook
Runs after a tool call finishes for Edit tool calls, running an inline shell check (2 commands). From epicsagas/epic-harness.
Hook
Runs when you submit a prompt, before the agent sees it, running recall-codex-hooks. From GiulioDER/RE-call.
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: