A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.
Hook
Runs when a session starts on startup, resume, clear, compact, startup, startup and resume, executing health-sentinel.sh and run-py.sh via bash with --session-start and --trigger (9 commands). From primeline-ai/evolving-lite.
Hook
Runs before the agent uses a tool for Bash, Write, Edit, Bash, Task, Task and Agent tool calls, executing run-py.sh and context-warning.sh via bash (4 commands). From primeline-ai/evolving-lite.
Hook
Runs when you submit a prompt, before the agent sees it, executing run-py.sh via bash (2 commands). From primeline-ai/evolving-lite.
Hook
Runs after a tool call finishes for Write, Edit, Bash, Task, Skill, Write, Edit, WebFetch, mcp__firecrawl__firecrawl_scrape, mcp__firecrawl__firecrawl_search, mcp__firecrawl__firecrawl_extract, mcp__firecrawl__firecrawl_crawl and mcp__firecrawl__firecrawl_agent tool calls, executing run-py.sh via bash (3 commands).…
Hook
Runs before the context is compacted for auto and manual tool calls, executing run-py.sh via bash. From primeline-ai/evolving-lite.
Hook
Runs when the agent finishes a response, executing session-summary.sh and run-py.sh via bash (4 commands). From primeline-ai/evolving-lite.