Plugin Claude Code
A plugin that turns Claude Code or Cowork sessions into structured documents such as weekly reports, architecture decision records, retrospectives, skills, and knowledge graphs. It uses a self-hosted service and web workspace to process the session.
Skill Claude CodeCodex
A tool workflow that turns a Codex conversation into a structured knowledge document. It can produce formats such as a weekly report, technical design, architecture decision record, incident review, book, reusable agent skill, or knowledge graph.
Skill Claude CodeCodex
A local knowledge search tool for finding project decisions, documents, and relationships between people, concepts, events, and other project items across previous sessions.
Plugin Claude Code
A Claude plug-in that turns a coding session into structured documents through a self-hosted service. It can produce weekly reports, technical plans, architecture decision records, retrospectives, books, skills, and knowledge graphs.
MCP server Claude CodeCodexCursor +2
TokenKnows MCP server — distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs and a knowledge graph on your self-hosted workbench. Runs locally from the tokenknows-mcp Python package. Needs 5 environment variables to run.
Command
A command that creates an Architecture Decision Record, or ADR: a short document explaining an important technical choice, its alternatives, consequences, and current status.
Command
A command that turns a long coding-agent conversation into a structured technical book with sections grouped into volumes, chapters, and subsections.
Command
A command that turns the current coding session into a six-part technical design document.
Command
A command that turns the current troubleshooting or bug-fixing session into a six-part incident review. An incident review records what happened, why it happened, how it was fixed, and what should improve.
Command
A command that turns the current session into a knowledge graph: a visual map of people, events, concepts, and artifacts linked by relationships. It is designed for conversations involving several people, decisions, documents, or tools.
Command
A command for listing documents distilled from the current project, such as reports, designs, incident records, books, and knowledge graphs. Distilled documents are shorter, structured records made from earlier work.
Command
A command for opening one distilled project document and showing all of its chapter content. It also provides extra information for knowledge graphs, which map entities and their relationships across documents.
Command
A workflow for extracting a reusable Agent Skill document from the current coding session. An Agent Skill is a saved set of instructions that an agent can use for a repeatable task later.
Command
A command that turns the current Claude session into a structured project weekly report covering progress, bugs, decisions, risks, and next steps. A session is one period of work with Claude.
Skill Claude CodeCodex
A skill that turns the current Claude conversation into a structured document through the TokenKnows service. It supports formats such as weekly reports, technical designs, architecture decision records, incident reviews, books, skills, and knowledge graphs.
Skill Claude CodeCodex
AUTO-CAPTURE — Use after EVERY meaningful user turn to persist the conversation into TokenKnows. Trigger on ANY user message that is NOT a one-word ack ("ok"/"thanks"). Without this skill, the conversation is silently lost from the user's TokenKnows workbench. Calls submitsessionevents MCP tool. This is the only path…
MCP server Claude CodeCodexCursor +2
TokenKnows MCP server — distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs and a knowledge graph on your self-hosted workbench. Runs locally from the tokenknows-mcp Python package. Needs 4 environment variables to run.