ScottRBK

Gather implementation context before planning or coding by delegating retrieval to subagents that combine Forgetful memory, local code inspection, Context7 documentation, and web search when needed. Use when the user asks to gather context, run context_gather, prepare an implementation brief, or check prior decisions and framework guidance before making changes.

Bootstrap a repository into Forgetful by creating or updating the project, memories, entities, relationships, documents, and code artifacts. Use when the user asks to encode a repo, bootstrap a codebase into memory, port the Claude /encode-repo workflow, or prepare a project for future agent context retrieval.

Create or initialize Forgetful project records for the current repository by matching the current working directory to an existing Forgetful project, asking before creating a missing project, and maintaining generic device/location metadata. Use when the user asks to initialize, create, register, or set up Forgetful project context.

Load recent Forgetful context for an already registered project by matching the current working directory to a Forgetful project and retrieving recent project-scoped memories. Use when the user asks to load, refresh, resume, or catch up on recent Forgetful project information.

Curate durable knowledge from the completed Codex turn into Forgetful memory. Use when asked to save or curate memory, or when the conversation produced reusable decisions, preferences, project knowledge, or technical patterns worth preserving.

Install or verify Forgetful dependencies for Codex by interactively configuring Forgetful MCP and optional Context7 MCP. Use when the user asks to install Forgetful, set up Forgetful for Codex, or check Forgetful dependencies.

Use when creating new memories to check for duplicates first, when discovering outdated information that should be marked obsolete, when new decisions supersede old ones, or when building connections between related knowledge in Forgetful MCP (mcp__forgetful__* tools).

Use when user asks "what do you know about X", when planning complex work that spans multiple topics, when investigating how concepts connect across projects, or when simple memory queries don't provide enough context. Deep traversal of Forgetful MCP knowledge graph (mcp__forgetful__* tools).

PROACTIVELY query Forgetful MCP (mcp__forgetful__* tools) when starting work on any project, when user references past decisions or patterns, when implementing features that may have been solved before, or when needing context about preferences. Save important decisions, patterns, and architectural insights to memory.

Architectural analysis workflow using Serena symbols and Forgetful memory. Use when analyzing project structure, documenting architecture, creating component entities, or building knowledge graphs from code.

Guidance for using Serena's LSP-powered symbol analysis. Use when exploring codebases, finding symbol definitions, tracing references, or when grep/text search would be imprecise.

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

Guidance for using Forgetful semantic memory effectively. Applies Zettelkasten atomic memory principles. Use when deciding whether to query or create memories, structuring memory content, or understanding memory importance scoring.

Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.

Guidance for using Forgetful semantic memory effectively. Applies Zettelkasten atomic memory principles. Use when deciding whether to query or create memories, structuring memory content, or understanding memory importance scoring.

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.

Use when you have made code changes and want another CLI agent to review them before committing or continuing. Covers crafting review prompts, scoping reviewer permissions to read-only, interpreting feedback, and follow-up clarification sessions.

Use when needing to programmatically invoke a CLI coding agent (Claude Code, OpenCode) from Python, delegate work to a sub-agent, or orchestrate multiple agents. Covers AgentShell instantiation, prompt execution, response streaming, session resumption, tool scoping, and cost tracking.