simba

Enforce Simba's Codex lifecycle routine for coding tasks. Use when starting or finishing implementation work in a Simba-enabled repo to run `simba codex-status` at start, handle any still-pending raw Codex transcript extraction, and run `simba codex-finalize` before final handoff.

Extract learnings from session transcripts and store in semantic memory database

Self-correcting memory recall — when recalled memories are ambiguous or conflicting, re-query for the specific entity (or ask) before answering, and never fabricate when memory is insufficient

Review recent memories and remove invalid or misleading ones from the semantic memory database

View statistics and recent entries from the persistent memory database. Shows session count, knowledge areas, facts, and recent activity.

Local hybrid search for markdown notes and docs. Use BEFORE reading files to save tokens - search first, read only what's relevant. Provides 90% token savings on exploration tasks.

Save the current work session to persistent memory for future context. Summarizes accomplishments, tracks files modified, and stores learnings for cross-session continuity.

Show token economics comparing usage with turbo-search vs without. Demonstrates actual savings from search-first approach.

Index the current project for optimized search with QMD semantic search and fast file suggestions. Run this when entering a new codebase or after significant changes. Saves 60-80% tokens on exploration tasks.

Analyze project markdown files and generate consolidated core instructions with SIMBA markers

Analyze project markdown instruction files and generate consolidated SIMBA core instructions with markers. Use when Codex needs to onboard a repo by reading CLAUDE.md/AGENTS.md and .claude docs, then producing .claude/rules/CORE_INSTRUCTIONS.md (or configured filename), updating core reference blocks, and verifying markers.