// Use when the user wants to migrate Codex state in ~/.codex into Agent Filesystem and mount the same shared Codex memory/settings across multiple computers. Recommends a .afsignore before migration and defaults to excluding worktrees, caches, logs, and temporary files.
Use when agents need persistent shared storage, when saving or restoring workspace state, or when coordinating file access across multiple agents and machines. Creates Redis-backed workspaces, checkpoints and restores agent state, mounts shared filesystems locally, searches workspace contents, and forks workspaces for parallel work.
Persistent Redis-backed workspaces for agents. Use via `afs mcp`, the `afs` CLI, sync mode, live mounts, and explicit checkpoints.
"Use before writing, modifying, or reviewing code when the {{serverName}} MCP server is connected. Read the relevant standards files live from standards/, cite the specific path you used, and treat the workspace as read-only."
"Use when Codex has access to the {{serverName}} AFS shared-memory MCP server, or when the user asks to check shared memory, prior cross-agent context, durable learnings, memory entries, workspace memory, saved commands, acronyms, aliases, shorthand such as CPP/CCP, /memory-search, or /memory-record. Before any non-trivial answer in a connected project, fresh-search /shared-memory for the task's key nouns, read relevant entries, and build on them instead of re-deriving. After discovering a durable reusable fact, write a new dated memory entry and append a pointer to /shared-memory/index.md. Skip trivial, purely conversational, or session-only tasks."
"Use when answering non-trivial questions in a project connected to the {{serverName}} MCP server (tools prefixed {{toolPrefix}}*). Read wiki/index.md first, search wiki/ for key nouns, cite relevant wiki paths, and offer to file durable answers back into the Shared LLM Wiki (Karpathy style). When ingesting sources from raw/, update source/topic/entity pages plus wiki/index.md and append to wiki/log.md."
"Use when coordinating project work through the {{serverName}} MCP server: reading the spec, claiming tasks, updating in-progress work, recording done work, or writing open questions. Preserve per-owner task files and append-only shared docs."
| name | codex-settings-sync |
| description | Use when the user wants to migrate Codex state in ~/.codex into Agent Filesystem and mount the same shared Codex memory/settings across multiple computers. Recommends a .afsignore before migration and defaults to excluding worktrees, caches, logs, and temporary files. |
Use this skill when the goal is to share Codex state across machines by moving ~/.codex into Agent Filesystem, then mounting that same Redis-backed volume on other computers.
~/.codex/.afsignore before migration.worktrees/.cache/, tmp/, logs/, *.log, *.tmp, *.pid, and *.sock as good default exclusions.worktrees/ as a choice point before migrating.Open the bundled starter ignore file at assets/.afsignore and adapt it to the user's needs.
agent-filesystem is built with make.afs to point at the shared Redis instance.~/.codex/.afsignore before migration../afs ws import --mount-at-source .codex ~/.codex.~/.codex, and the workspace name is .codex.~/.codex, choose mount mode with ./afs config set --mode mount if you want a live mount there, then run ./afs ws mount .codex ~/.codex../afs status and ls -la ~/.codex.Point the CLI at the same control plane or Redis database. Then run
./afs config set --mode mount for live mount mode, or
./afs config set --mode sync for sync mode, before mounting .codex at
that machine's ~/.codex.
afs ws import honors ~/.codex/.afsignore if present..afsignore uses .gitignore-style pattern syntax.worktrees/ is usually safer than syncing it.~/.codex from multiple active computers at the same time..local-backup directories until the setup is stable.Source machine rollback:
./afs ws unmount ~/.codex
Secondary machine rollback:
./afs ws unmount ~/.codex
rm -rf ~/.codex
mv ~/.codex.local-backup ~/.codex