LLM hooks

571 tagged LLM, measured the same way as everything else here.

Browse within: Multi-Agent 37agent-memory 32knowledge-graph 27context-management 23ai-memory 21coding-agents 20knowledge-base 20local-first 20embeddings 19markdown 18sqlite 14long-term-memory 13agentic-workflow 12obsidian 12

PreToolUse

25

LLMQuant/quant-mind

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing pre_tool_use_no_bypass.py via python3. From LLMQuant/quant-mind.

2.8k +24 18d ago A tokens not measured original MIT

UserPromptSubmit

27

PolyArch/humanize

Hook

Part of humanize

Runs when you submit a prompt, before the agent sees it, executing loop-plan-file-validator.sh. From PolyArch/humanize.

1.4k +6 6d ago A tokens not measured

PreToolUse

28

PolyArch/humanize

Hook

Part of humanize

Runs before the agent uses a tool for Write, Edit, Read and Bash tool calls, executing loop-write-validator.sh, loop-edit-validator.sh, loop-read-validator.sh and loop-bash-validator.sh (4 commands). From PolyArch/humanize.

1.4k +6 6d ago A tokens not measured

PostToolUse

29

PolyArch/humanize

Hook

Part of humanize

Runs after a tool call finishes for Bash tool calls, executing loop-post-bash-hook.sh. From PolyArch/humanize.

1.4k +6 6d ago A tokens not measured

SessionStart

30

yohey-w/multi-agent-shogun

Hook Claude Code

Runs when a session starts, executing session_start_hook.sh via bash. From yohey-w/multi-agent-shogun.

1.4k +1 27d ago A tokens not measured original MIT

Stop

31

yohey-w/multi-agent-shogun

Hook Claude Code

Runs when the agent finishes a response, executing stop_hook_inbox.sh via bash. From yohey-w/multi-agent-shogun.

1.4k +1 27d ago A tokens not measured original MIT

SessionStart

32

dyoshikawa/rulesync

Hook Claude Code

Runs when a session starts, running an inline shell check. From dyoshikawa/rulesync.

1.4k +11 2d ago A tokens not measured original MIT

PreCompact

33

TrafficGuard/typedai

Hook

Part of knowledge

Runs before the context is compacted, executing extract-kb.sh. From TrafficGuard/typedai.

1.2k 8mo ago A tokens not measured copy · 56% MIT

SessionStart

34

nvk/llm-wiki

Hook

Runs when a session starts, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.

1.2k +12 6d ago A tokens not measured original MIT

PreCompact

35

nvk/llm-wiki

Hook

Runs before the context is compacted, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.

1.2k +12 6d ago A tokens not measured copy · 89% MIT

PostCompact

36

nvk/llm-wiki

Hook

Runs after the context is compacted, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.

1.2k +12 6d ago A tokens not measured copy · 84% MIT

PreToolUse

37

melandlabs/openloomi

Hook

Part of claude

Runs before the agent uses a tool for Bash, Edit, Write, Read, Grep and Glob tool calls, executing loomi-bridge.mjs via node with --event. From melandlabs/openloomi.

1.0k 9d ago A tokens not measured original Apache-2.0

Stop

38

melandlabs/openloomi

Hook

Part of claude

Runs when the agent finishes a response, executing loomi-bridge.mjs via node with --event (2 commands). From melandlabs/openloomi.

1.0k 9d ago A tokens not measured original Apache-2.0

Notification

39

melandlabs/openloomi

Hook

Part of claude

Runs when the agent sends a notification for permission_prompt and elicitation tool calls, executing loomi-bridge.mjs via node with --event. From melandlabs/openloomi.

1.0k 9d ago A tokens not measured original Apache-2.0

PostCompact

40

tomasz-tomczyk/crit

Hook Claude Code

Runs after the context is compacted, running echo 'REMINDERS (things linters dont catch): 1) Verify all s. From tomasz-tomczyk/crit.

979 4d ago A tokens not measured original MIT

PermissionRequest

41

tomasz-tomczyk/crit

Hook

Part of claude-code

Runs when the agent asks permission for an action for ExitPlanMode tool calls, running crit plan-hook. From tomasz-tomczyk/crit.

979 4d ago A tokens not measured original MIT

SessionStart

42

Pipelex/pipelex

Hook Claude Code

Runs when a session starts, executing session-start.sh. From Pipelex/pipelex.

852 3d ago A tokens not measured copy · 52% MIT

PostToolUse

43

Pipelex/pipelex

Hook Claude Code

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing check-keyword-only.sh. From Pipelex/pipelex.

852 3d ago A tokens not measured copy · 48% MIT

PostToolUse

45

hoophq/hoop

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, executing gofmt.sh. From hoophq/hoop.

805 yesterday A tokens not measured copy · 42% MIT

PreToolUse

46

assistant-ui/tool-ui

Hook Claude Code

Runs before the agent uses a tool for Bash(git add*) and Bash(git commit*) tool calls, running an inline shell check (2 commands). From assistant-ui/tool-ui.

773 3mo ago A tokens not measured original MIT

SessionStart

47

assistant-ui/tool-ui

Hook Claude Code

Runs when a session starts, running an inline shell check (2 commands). From assistant-ui/tool-ui.

773 3mo ago A tokens not measured original MIT

Stop

48

hex/claude-council

Hook

Part of claude-council

Runs when the agent finishes a response, executing stop-review-gate.sh via bash. From hex/claude-council.

673 7d ago A tokens not measured copy · 50% MIT

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: