By tmdgusya
Auto-export and parse your Claude Code conversation transcripts. Extracts only user prompts from sessions.
A Claude Code plugin that automatically exports your conversation prompts when sessions end.
.transcriptor/ in each projectgit clone https://github.com/tmdgusya/claude-vocab ~/.claude/plugins/claude-vocab
Just use Claude Code normally. When you exit a session (/exit, Ctrl+C, etc.), your prompts are automatically saved to:
.transcriptor/prompts-YYYYMMDD_HHMMSS.txt
/export-prompts — Export prompts from a specific session/list-exports — List all exported transcripts in current projectEach prompt is saved on its own line, in chronological order:
How do I create a React component?
Can you add error handling to this function?
Make the button blue instead of green
The plugin uses a SessionEnd hook that:
type: "user" messages<).transcriptor/ directoryjq command-line tool (usually pre-installed on macOS/Linux)MIT
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 tmdgusya/claude-vocabEngineering discipline skills: optimization rules, systematic debugging, AI slop cleanup, and implementation guardrails
영어 프롬프트 학습 도우미 - 어휘력 확장 및 자연스러운 표현 학습
클럽의 샌드위치 가게 - Subway 주문 시스템
Generate minimal, effective AGENTS.md files using the Differential Context principle. Based on research showing verbose context files reduce agent performance.
Implementation agents with planning, building, and loop control workflows using IMPLEMENTATION_PLAN.md with continuous task execution, verification, git workflow, and iteration limits
Session transcript timeline viewer for Claude Code and Codex agent sessions
Persistent 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.
Session log archiver: saves conversations as Markdown or JSON for easy review
qrec session recall engine
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.