primeline-ai

primeline-ai/evolving-lite

Plugin Claude Code

Self-evolving Claude Code system that learns from corrections, manages context, and improves every session.

primeline-ai/evolving-lite

Agent

Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.

primeline-ai/evolving-lite

Agent

Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations.

primeline-ai/evolving-lite

Agent

Checks Evolving Lite data consistency - memory structure, experience index, config validity.

primeline-ai/evolving-lite

Agent

Fixes issues found by integrity-checker - repairs JSON, rebuilds indices, fixes permissions.

primeline-ai/evolving-lite

Agent

Reviews and refines plans - checks for anti-patterns, missing kill criteria, vague gates.

primeline-ai/evolving-lite

Agent

Generates session handoff documents with project state and next steps.

primeline-ai/evolving-lite

Command

Show context window usage, active tier, and system stats.

primeline-ai/evolving-lite

Command

Create a new custom slash command.

primeline-ai/evolving-lite

Command

Create a new custom automation hook.

primeline-ai/evolving-lite

Command

Systematic debugging with hypotheses and evidence gathering.

primeline-ai/evolving-lite

Command

Show what the system learned and changed recently.

primeline-ai/evolving-lite

Command

Check for updates and update Evolving Lite.

primeline-ai/evolving-lite

Command

Switch to Haiku model (fast, cheap).

primeline-ai/evolving-lite

Command

Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.

primeline-ai/evolving-lite

Command

Switch to Opus model (maximum quality).

primeline-ai/evolving-lite

Command

Plan a complex project with discovery, structure, and kill criteria.

primeline-ai/evolving-lite

Command

Explicitly save something to memory as an experience.

primeline-ai/evolving-lite

Command

Structured code review with severity categorization (distinct from Claude Code's PR review).

primeline-ai/evolving-lite

Command

Switch to Sonnet model (balanced).

primeline-ai/evolving-lite

Command

Adversarial brainstorming - challenge ideas, find weaknesses.

primeline-ai/evolving-lite

Command

Apply structured thinking frameworks to a problem.

primeline-ai/evolving-lite

Command

Show current project status and suggest next steps.

primeline-ai/evolving-lite

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.