MCP server Claude CodeCodexCursor +2
MCP server "cross-session-memory-bridge" as configured in NovasPlace/CSM. Runs ./runtime/launch-mcp.mjs with node. Needs 2 environment variables to run.
41 8d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for NovasPlace/CSM, covering goal, constraints & preferences, lint debt classification (locked), progress and done.
41 8d ago A 2,553 tokens
original MIT
SessionStart
03Hook
Runs when a session starts, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
PreToolUse
05Hook
Runs before the agent uses a tool, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
copy · 78% MIT
Hook
Runs when the agent asks permission for an action, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
PostToolUse
07Hook
Runs after a tool call finishes, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
PreCompact
08Hook
Runs before the context is compacted, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
PostCompact
09Hook
Runs after the context is compacted, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
original MIT
Hook
Runs when a subagent starts, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
copy · 83% MIT
SubagentStop
11Hook
Runs when a subagent finishes, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
copy · 91% MIT
Stop
12Hook
Runs when the agent finishes a response, executing run-hook.mjs via node. From NovasPlace/CSM.
41 8d ago A
tokens not measured
copy · 89% MIT
Skill Claude CodeCodex
Coordinate Git and Cross-Session Memory as version control for agent work. Use when Codex needs AgentBook status, checkpoints, history, resume or handoff, provenance, isolated agent approaches, semantic comparison, or an evidence-backed game-development tuning and playtest iteration with an explicit keep or revert…
41 8d ago A 65 tokens
original MIT
Skill Claude CodeCodex
Use the complete native Cross-Session Memory (CSM) runtime for continuity, memory governance, living state, beliefs, self-model, AgentBook, checkpoints, context cache, goals, work ledger, compaction, re-entry, or handoff across Codex tasks.
41 8d ago A 60 tokens
original MIT
Plugin Claude Code
The complete self-hosted Cross-Session Memory runtime and lifecycle automation, native to Claude Code.
41 8d ago A
tokens not measured
original MIT
Agent
Memory governance specialist. Use for deduplicating, reviewing, merging, and archiving project memory. Previews first; performs merges or deletions only when explicitly requested.
41 8d ago A 41 tokens
original MIT
Agent
Session-start continuity specialist. Use when resuming work to assemble re-entry context and a task brief from prior sessions, verified against the current workspace.
41 8d ago A 37 tokens
original MIT
Agent
Handoff specialist. Use before stopping, compaction, or transferring work to checkpoint expensive state and write a concrete handoff summary.
41 8d ago A 33 tokens
original MIT
Command
Read AgentBook state and events, or manage AgentBook rules.
41 8d ago A 13 tokens
original MIT
csm-beliefs
20Command
Review belief knowledge, run a belief scan, and preview promotions.
41 8d ago A 13 tokens
original MIT
csm-brief
21Command
Build a context brief for the current task from prior sessions.
41 8d ago A 12 tokens
original MIT
Command
Create or inspect durable checkpoints of expensive-to-reconstruct state.
41 8d ago A 12 tokens
original MIT
Command
Show context pressure and audit compaction behavior.
41 8d ago A 9 tokens
original MIT
csm-goals
24Command
List, set, or update tracked goals for this project.
41 8d ago A 12 tokens
original MIT