antahkarana
Multi-perspective reasoning through cognitive voices
checkpoint
Capture moment of clarity before moving forward
codebase-learn
Learn codebase structure with tree-sitter + SSL patterns
epsilon-yajna
Convert verbose memories to SSL v0.4 format - I am encoder AND decoder
explore
RLM-style recursive memory exploration - dynamically navigate the memory graph
cc-soul-daemon
Start, stop, or check the chittad daemon
cc-soul-mcp
Configure chitta MCP server for direct tool access (mcp__chitta__*)
cc-soul-setup
Build cc-soul from source (requires cmake, make, C++ compiler)
cc-soul-shutdown
Gracefully stop the cc-soul daemon
cc-soul-update
Update cc-soul binaries (downloads pre-built or builds from source)
distill-pending
Process pending transcript distillation
init
Initialize soul with foundational beliefs and wisdom
dream
Trigger autonomous curiosity-driven exploration. The soul picks a topic from memory gaps or curiosity seeds, searches the web, and stores what it finds as dream-tagged memories.
health
Soul system health check with remediation
hint-corpus
Fine-tune the Qwen3-0.6B hint model — corpus gen, LoRA/unsloth, GGUF export, Ollama
introspect
Soul self-examination (Svadhyaya)
kriya
Review soul discoveries (fixes, improvements, corrections) one by one, accept or discard each, implement accepted ones, build chitta, and optionally release.
learn
Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.
locomo-benchmark
Run LoCoMo benchmark for long-term conversational memory
long-task
Initialize or resume a long-running task session. Use when starting a complex multi-session task, resuming work from a previous session, or when the user mentions claude-progress.json or long-running work.
mermaid
Render Mermaid diagrams as ASCII/Unicode art or SVG
migrate
Import soul data from SQLite or shared chitta files
prog-review
First-principles review — question requirements, delete unnecessary parts, simplify, optimize with evidence, automate last. Use for code review, refactor, performance, or architecture.
reawaken
Restore context and momentum via Pratyabhijñā (recognition)
recap
Token-savvy session continuation. Rebuilds working context from transcript + soul memories in ~1500 tokens instead of replaying full history. Use when starting a new session to continue previous work.
remember
Quickly save a memory to the soul
resume
Resume a thread by loading its ~800-token context capsule
shepherd
Autonomous pipeline monitor using sense-think-act loop. Watches snakemake/nextflow jobs, detects errors, applies fixes from memory, restarts on failure.
tasks
Browse and resume tasks, threads, and background jobs across sessions
ultrathink
First-principles deep thinking for significant problems
yajña
Autonomous development ritual with role-based coordination. Loops until complete using specialized agents (hotṛ→research, adhvaryu→implement, udgātṛ→test).