Command
Part of token-warden
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
518 tagged agent-memory, measured the same way as everything else here.
Browse within: claude-flow 60docker 60ai-memory 57knowledge-graph 48Orchestration 38desktop-agent 38operating-room 38second-brain 38local-first 34cuda 29holographic-memory 29knowledge-base 24knowledge-management 24ai-coding-agents 20
Command
Part of token-warden
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
Command
Part of rembric
Show recent memory context for this project.
Command
Part of rembric
Search Rembric for prior context matching the query.
Command
Part of rembric
Persist an end-of-session summary to Rembric (summary ≤10000 chars).
Command
Search and load past AI coding sessions from Squish memory.
Command Claude Code
A command that summarizes CodeBrain's operational status, including checks, background workers, queued jobs, and indexed files.
Command Claude Code
A command that compares two versions of code-brain context search and reports ranking, repeatability, storage, latency, and context-size results.
Command Claude Code
A command that reports Code Brain activity, including Claude and Codex token use, hook and MCP activity, and blocked tool calls. Hooks are automatic project actions, while MCP is a way for an agent to call connected tools.
Command Claude Code
Archive multiple completed changes at once.
Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
Command Claude Code
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
Command Claude Code
Part of memory-layer
Show active memories loaded for the current context.
Command Claude Code
Part of memory-layer
Record feedback on whether a memory helped (worked/failed/partial).
Command Claude Code
Part of memory-layer
Explicitly search memories (usually handled automatically by Agent Skills).
Command
Part of commitlore
Read and write the repository's unattended-capture setting — commitlore auto status|on|off.
Command
Sweep a repo's triage-labeled backlog — vet every issue against the code, fix the easy ones in one cleanup PR, and label the rest priority → area → descriptors, with epics grouped and ranked. Repo-agnostic: discovers each repo's label taxonomy at runtime.
Command
One cycle of the perpetual delivery loop — size to the machine, fix a batch, audit, file what you cannot fix, benchmark against Claude Code, ship, recalibrate. Never terminates.
Command
Part of unforgit
Search Unforgit memory for context relevant to the user's current request.
Command
Part of unforgit
Save durable project knowledge to Unforgit.
Command
Part of unforgit
Show Unforgit repository-memory status and suggest the next useful action.
Command
Part of artel
Save an Artel session handoff so the next session or agent can continue.
Command
Part of artel
Write a fact, decision, or gotcha to Artel shared memory.
Command
Part of artel
Show open Artel tasks, or claim and start the next one.
Command
Part of nautilus-compass
Summarize drift signals (green / yellow / red) across recent sessions: distribution, timeline, top yellow signals, and red incident details.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: