By JoelYYoung
Navigate AI conversation logs like a debugger. Use when analyzing past agent sessions, understanding what happened in a conversation, building custom log readers, or extracting workflows and lessons from session data.
Analyze one or more sessions: drill from overview → turns → tool calls, map phases, and produce an analysis artifact.
Connect RetroLens to a log directory: choose a project scope, configure the log path, and verify the connection.
Extract reusable human lessons and agent directives from a session analysis.
Discover where AI conversation logs are stored and get started with RetroLens.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub joelyyoung/retrolens --plugin retrolensPersistent local memory for Claude Code. Every tool call, every file edit, every thinking block from every session — stored verbatim on your machine. Semantic recall in ~126ms with zero API calls.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
Meta-Cognition tool for Claude Code: session history analysis, workflow optimization, and 21 MCP tools for deep session insights.
Mine your SpecStory coding histories (Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence and outcome labels, and forge the ones you choose into skills installed across every agent harness.
Session transcript timeline viewer for Claude Code and Codex agent sessions
ax - the agent experience layer. Local graph of every Claude Code + Codex session, skill invocation, edit, and commit. Surfaces what to use, what to ground on, and which experiments to package next.