LLM-driven session retrospection skill: detects friction in agent sessions and materializes learnings into correct destinations (user-memory, project-rules, skill PRs, checkpoints, harness artefacts)
A Claude Code skill that catches the process mistakes silently draining your sessions — unverified "done" claims, repeated regressions, wasted tokens.
Local-first Codex session continuity with bounded evidence, editable Markdown ledgers, usage/cost accounting, and a Codex Skill.
Reviews how a Claude Code session was conducted rather than what it shipped, classifies its shape, scores the run, flags where the context window went, and turns repeated hand-work into wire-ins for the skills the session used
Static, privacy-aware Kanban review surface for AI coding session-to-task extraction
Add a description, image, and links to the session-review topic page so that developers can more easily learn about it.
To associate your repository with the session-review topic, visit your repo's landing page and select "manage topics."