compress
265Command
Compress project memory. Archives older entries from MEMORY.md into archive.md to keep the hot layer lean. Run when memory-loop warns about file size.
2,911 tagged Memory and context, measured the same way as everything else here.
Browse within: agent-memory 167ai-memory 113knowledge-management 109obsidian 62claude-plugin 57ai-assistant 53claude-ai 53knowledge-base 47markdown 47local-first 41embeddings 38claude-desktop 36knowledge-graph 36gemini-cli 35
Command
Compress project memory. Archives older entries from MEMORY.md into archive.md to keep the hot layer lean. Run when memory-loop warns about file size.
Command
Save current session work to project memory. Updates MEMORY.md with completed tasks, decisions, and discoveries from this session.
Command
Show project memory status: file size, section counts, and whether compression is recommended.
Command Claude Code
Skill này chạy tự động khi /use-contextd không resolve được config của codebase, hoặc gọi trực tiếp để kiểm tra trạng thái tích hợp contextd của dự án hiện tại.
ralfstrobel/agentic-brownfield-coding
Command
Part of abc
Codify implicit codebase knowledge as agent rules.
Command
Part of subcog
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
Command
Part of hades
Show pending Asphodel memory update proposals.
Command Claude Code
A command that turns raw files in a knowledge folder into linked, structured wiki pages. A wiki is an organized set of reference pages; here, the command identifies entities, concepts, parameters, and signals from source documents.
Command
Part of claude-teams-brain
Approve, reject, or manage pending brain memories.
Command
Part of claude-teams-brain
Store a persistent rule or convention that will be injected into all future teammates.
Command
Part of claude-teams-brain
Show brain and session stats — tasks indexed, decisions captured, token savings.
Command
Part of openltm
USE WHEN running schema migrations, scanning memories for secrets, or managing the LTM graph visualization server. Groups migrate | scan | server.
Command
Part of openltm
USE WHEN checking memory health, reviewing project scores, inspecting janitor status, or diagnosing why memories are decaying. Shows health scores, decay summary, activity log, and log health.
Command
Part of openltm
USE WHEN recalling past decisions, storing new insights, forgetting stale memories, linking memories, or reviewing pending memory proposals. Groups recall | learn (with optional --save-context) | forget | relate | propose.
Command
Part of claude-combine
Load the most recent session file from /.claude/session-data/ and resume work with full context from where the last session ended.
Command
Part of claude-combine
Save current session state to a dated file in /.claude/session-data/ so work can be resumed in a future session with full context.
Command
Part of business-consulting
Set the client context so all subsequent analyses are automatically tailored — store client name, industry, size, geography, and key facts.
yesheng-oss/context-mcp-subgraph
Command
Part of context-mcp
Call the context MCP tool with action: "resume", project: "$ARGUMENTS" (if no argument given, infer the project name from the current working directory name), and rootPath: " ".
yesheng-oss/context-mcp-subgraph
Command
Part of context-mcp
Call the context MCP tool with action: "save" to store a note for the current project.
drleadflow/ghl-automation-builder
Command Claude Code
Manually write a session-end summary + update ACTIVE-CONTEXT.md. Use before quitting if the auto-hook doesn't fire or when you want to control what gets captured.
drleadflow/ghl-automation-builder
Command Claude Code
Catch up at session start. Reads ACTIVE-CONTEXT.md + last 3 session summaries + recent DECISIONS.md entries to restore context in ≤30 seconds.
Command
Save session state before context loss.
Command
Restore context from last checkpoint at session start.
Command
Analyze recent checkpoints to surface learnings and suggest memory updates.
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: