// "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."
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 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 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."
| name | {"[object Object]":null} |
| description | 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. |
This skill coordinates a shared project board stored in Agent Filesystem and
exposed as MCP server {{serverName}}. Multiple humans and agents may write
to this workspace, so keep ownership clear and avoid broad rewrites.
If you do not already know the user's handle, ask for a short stable handle
such as alice or frontend. Use that handle in every task file you
create or update.
plan/spec.md and plan/roadmap.md.tasks/backlog.md.tasks/in-progress/ with
{{toolPrefix}}file_list at depth 2 so you do not duplicate active
work.tasks/in-progress/<handle>-<slug>.md with owner, date, progress,
goal, plan, and log sections.tasks/backlog.md.Append dated notes to your own in-progress file. Do not edit another owner's
in-progress file. Shared files such as plan/spec.md,
plan/roadmap.md, and questions/*.md should grow by focused additions
instead of rewrites.
tasks/done/<slug>.md.checkpoint_create is available, create a milestone checkpoint with a
short descriptive name.