Command Claude Code
Run the decision review — process expired decisions by weight.
not rated 7 yesterday A 10 tokens
original MIT
discover
02Command Claude Code
Build or refresh the on-demand discovery map (concept graph + per-node notes).
not rated 7
changed 15d ago A 16 tokens
original MIT
Command Claude Code
Run the memory review — staleness, duplicates, graduation candidates.
not rated 7 yesterday A 13 tokens
original MIT
PreToolUse
04Hook Claude Code
One of 5 in settings.json
Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing pre-protect-secrets.sh. From lx-wnk/Agent-Context.
not rated 7
changed 17d ago A
tokens not measured
original MIT
PostToolUse
05Hook Claude Code
One of 5 in settings.json
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post-format.sh. From lx-wnk/Agent-Context.
not rated 7
changed 17d ago A
tokens not measured
original MIT
Stop
06Hook Claude Code
One of 5 in settings.json
Runs when the agent finishes a response, executing stop-test-gate.sh. From lx-wnk/Agent-Context.
not rated 7
changed 17d ago A
tokens not measured
original MIT
SubagentStop
07Hook Claude Code
One of 5 in settings.json
Runs when a subagent finishes, executing subagent-scope.sh. From lx-wnk/Agent-Context.
not rated 7
changed 17d ago A
tokens not measured
original MIT
Settings file Claude Code
One of 5 in settings.json
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, Stop, SubagentStop).
not rated 7
changed 17d ago A
tokens not measured
original 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: