ScottRBK

Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature…

Gather deep context before planning or implementing — one pass that turns a task description into a cited context pack: relevant decisions, patterns, constraints, code pointers, procedures, and explicit gaps. Runs recall from several angles, explores the…

Encode a repository into the Forgetful knowledge base — bootstrap the project, its entities, memories, and documents from the codebase itself. Use when bringing a new repo under Forgetful or refreshing a stale encoding. Re-encoding is an update pass:…

Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another…

Explore the Forgetful knowledge graph when flat search isn't enough — cross-project investigations, "what do we know about X", entity-centred questions, tracing how decisions connect. Use when recall returns fragments that reference entities or trail across…

Recall past knowledge before working — prior decisions, solved problems, preferences, project history. Use at the start of any task, when the user references earlier work, when re-entering a project after time away, or before proposing an approach that may…

Remember knowledge worth keeping — a decision made, a solution found, a preference stated, a pattern confirmed. Use when work surfaces something future sessions will need, or the user asks to remember something. Routes content to the right store (memory,…

File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets. Use when a binary artifact is worth keeping alongside knowledge, or when a stored procedure needs a bundled asset. The description is the entire search surface: say what…

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…

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…

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…

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…

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…

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…

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…

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.

Monitor and interpret evaluation runs of the eval-harness framework. Use when asked to watch, interpret, debug or diagnose an eval run, its logs, its scores or its results.

Create eval-harness evaluations. Use when the user wants a new evaluation for a CLI coding agent (Claude Code, OpenCode, Copilot, Codex, Pi, Cursor, Grok).

Run evaluations with the eval-harness framework. Use when asked to run, execute, benchmark or compare CLI coding agents (Claude Code, OpenCode, Copilot, Codex, Pi, Cursor, Grok) on existing evals.

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…

Use when invoking a CLI coding agent from Python, delegating to a sub-agent, discovering available model strings, orchestrating agents, streaming output, resuming sessions, restricting tools, or checking agent/model health. Supports Claude Code, OpenCode,…

Use when you have made code changes and want another CLI agent to review them before committing or continuing — a second-opinion, security, correctness, requirements, or test-coverage review, or a cross-agent independent review. Keywords: reviewer agent,…

Multi-phase repository encoder for the Forgetful knowledge base. Activate when the user asks to "encode this repo", "bootstrap forgetful for project X", "populate the knowledge base from this codebase", or runs `hermes forgetful encode`. Walks the repo…

Query and analyse a .mycelium.json structural map produced by the Mycelium static analysis tool. Use when exploring codebase architecture, understanding project structure, or reviewing Mycelium output files.