Navigate codebases and manage caches via the basemind CLI — outlines, symbol search, reference/caller lookups, git history, blame, and diffs. For headless scripting, CI, or when driving the CLI more efficiently than interactive MCP calls. Shares the same index as the MCP server.
Navigate large or unfamiliar codebases via the basemind MCP server — outlines, symbol search, reference/caller lookups, commit history, blame, and diffs without reading source files. Reach for it whenever the user asks "where is X defined", "what calls Y", "what changed recently in Z", or whenever you're about to grep…
Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.
Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion codemap.md navigation maps — against Claude 5 context-engineering rules (judgement over rules, progressive disclosure, no cross-layer conflicts). Asks whether to optimize the current repository…
Turn a codebase directory and a business question into a single interactive HTML code map, or turn a described non-code business process into the same evidence-backed map. Use when the user asks to explain, map, or visualize code flows, architecture, modules, data models, or a business process.
Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.
Create, repair, and maintain CLASSMAP.md, a lightweight code responsibility map for a project. Use when onboarding to an existing codebase, when CLASSMAP.md is missing, stale, incomplete, or contradicts code, after major refactors, after adding important modules, or when the user asks to refresh the code map. This…
Use CLASSMAP.md to route feature requests, bug reports, refactors, and behavior changes to the smallest accurate set of relevant code units. Use before coding when the user asks where to change behavior, which class or file owns a feature, where a bug may live, or how to implement a change with minimal search. This…
Run otito context before editing — task-aware primary files, tests, patterns, and validation commands. Invoke explicitly before planning or implementing a change.
Self-evaluates otito context packs against expected files/symbols, records labeled gaps as eval corpus cases, and implements ranking/extractor fixes when retrieval fails. Use when otito missed the right file, hotspots were wrong, the user says otito was not useful, or asks to self-evaluate / auto-improve otito.…