PreCompact
49Hook
Part of stitch-kit
Runs before the context is compacted for auto and manual tool calls, executing pre-compact.mjs via node (2 commands). From gabelul/stitch-kit.
257 tagged Memory and context, measured the same way as everything else here.
Browse within: agent-memory 34ai-memory 20context-engineering 12codex-cli 8knowledge-graph 8local-first 7claude-code-hooks 6context 6knowledge-management 6llm-agents 6gemini-cli 5hybrid-search 5plugin 5
Hook
Part of stitch-kit
Runs before the context is compacted for auto and manual tool calls, executing pre-compact.mjs via node (2 commands). From gabelul/stitch-kit.
FlorianBruniaux/claude-code-plugins
Hook
Part of ai-methodology
Runs after a tool call finishes, executing learning-capture.sh via bash. From FlorianBruniaux/claude-code-plugins.
Hook
Part of memem
Runs when you submit a prompt, before the agent sees it, executing auto-recall.sh via bash. From TT-Wang/memem.
Hook
Part of memory-kit
Runs when a session ends, executing session-end.sh via bash. From awrshift/claude-memory-kit.
Hook
Part of mnemos-memory
Runs before the context is compacted, running an inline shell check. From anthony-maio/mnemos.
Hook
Part of openltm
Runs before the context is compacted, executing run-hook.sh. From RohiRIK/OpenLtm.
Hook
Part of context-kernel
Runs when you submit a prompt, before the agent sees it, executing symptom_slice.py via python3. From Pinperepette/context-kernel.
Hook
Part of context-kernel
Runs before the context is compacted, executing precompact_snapshot.py via python3. From Pinperepette/context-kernel.
Hook
Part of memxt
Runs before the context is compacted, executing hook.sh. From Yupcha/memXT.
Hook
Part of mistakebook
Prompt-submission hooks are automatic commands that run before an AI coding agent receives your message. They react to selected phrases and can also run a preparation check for every prompt.
Hook Claude Code
Runs before the context is compacted, executing pre-compact-flush.py. From TheSmokeDev/taskchad-os.
Hook Claude Code
Runs before the context is compacted, executing precompact-snapshot.sh. From badwally/TheKnowledge.
Hook
Part of m3
Runs when a session starts, running an inline shell check. From skynetcmd/m3-memory.
Hook
Part of m3
Runs before the context is compacted for auto tool calls, running an inline shell check. From skynetcmd/m3-memory.
Hook Claude Code
Runs before the context is compacted, executing precompact_save.sh via bash. From walm00/business-context-os.
Hook Claude Code
Runs when a session starts on startup, compact and clear, executing load-memories.sh (3 commands). From redhat-ai-americas/memory-hub.
Hook
Part of minns-agent
Runs when the agent finishes a response, running minns learn --category session_summary --from-stdin. From Minns-ai/MinnsDB.
Hook
Part of minns-agent
Runs before the agent uses a tool for Edit and Write tool calls, running minns recall --brief --file $TOOL_INPUT_FILE_PATH 'relevant . From Minns-ai/MinnsDB.
synthesisengineering/synthesis-skills
Hook
Part of synthesis-skills
Runs when a session starts, executing session_context.py via python3 with --format. From synthesisengineering/synthesis-skills.
Hook
Part of memo
Runs when you submit a prompt, before the agent sees it, running an inline shell check (4 commands). From jagoff/memo.
Hook
Part of memory-toolkit
Runs before the context is compacted, executing session-save.js via node. From IlyaGorsky/memory-toolkit.
Hook
Runs when you submit a prompt, before the agent sees it, executing PromptProcessing.hook.ts, SatisfactionCapture.hook.ts, ReminderRouter.hook.ts and MemoryTurnStart.hook.ts (4 commands). From DorShaer/Husk.
Hook Claude Code
Runs before the context is compacted, executing context-usage-monitor.js via node with --precompact. From Global-mindee/WAY.
Hook Claude Code
Runs before the context is compacted, running mulch prime. From FortiumPartners/ensemble.
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: