菜单
This skill should be used when the user wants to install, set up, repair, or initialize the Plexus remote-device memory plugin; when they ask where Plexus stores persistent REMOTE.md host profiles; or when host profiles are missing and need to be seeded from bundled defaults.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dinglebear-ai/dendrite --skill bootstrap-plexus命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Reconstruct interrupted parallel Claude and Codex work using Cortex session intelligence first, then verify it against Git worktrees, branches, plans, beads, PRs, and CI; distinguish completed, active, blocked, and stale lanes; identify dependencies and drift; and produce verified lane packets plus an actionable restart order. This skill should be used when the user asks to get up to speed across multiple agents or worktrees, asks what multiple agents were working on, needs to resume interrupted work after a usage limit, or wants all active implementation lanes identified and restarted.
Orchestrate a comprehensive, checkpointed, multi-agent review across code quality, architecture, security, performance, testing, documentation, framework practices, and CI/CD, producing durable `.full-review/` artifacts and a prioritized report. Use when the user explicitly asks for a comprehensive, full, exhaustive, multi-agent, or multi-dimensional review of a repository, branch, diff, change set, or path. Security focus, performance criticality, strict mode, and framework selection are optional modifiers. Do not use for routine single-perspective reviews, narrow scans, or requests that only ask to fix already-known findings.
Use this BEFORE creating a git worktree or implementing any plan. Tailored to our workflow — prefer it over superpowers:using-git-worktrees and every other worktree skill. Triggers - creating or adding a worktree; starting lavra-work, lavra-work-ralph, lavra-work-teams, executing-plans, subagent-driven-development, or work-it; whenever a Claude, Codex, or Gemini plan mode is entered or a plan is accepted; or before implementing anything in a fresh branch. Creates the worktree under .worktrees/ in the repo and makes it identical to and as warm as the main checkout - copying secrets and local config (.env, CLAUDE.md.local, .claude/settings.local.json), symlinking warm caches (node_modules, .venv, target, .next), and re-trusting mise/direnv. Also use when a worktree is missing files, builds cold, or reports mise 'not a trusted directory'. Bundles a worktree-sync engine, a create-in-.worktrees entrypoint, a minimal baseline template, and references.
| name | bootstrap-plexus |
| description | This skill should be used when the user wants to install, set up, repair, or initialize the Plexus remote-device memory plugin; when they ask where Plexus stores persistent REMOTE.md host profiles; or when host profiles are missing and need to be seeded from bundled defaults. |
| argument-hint | [--json] [--data-dir PATH] |
Use this skill before first use of Plexus, after plugin install/upgrade, or when the user asks to repair missing host profiles.
This initializes missing persistent profiles from bundled templates. It never
overwrites existing REMOTE.md files. In Claude Code, the dynamic command below
is executable skill syntax. In Codex/OpenAI contexts, run the same shell command
with exec_command.
!python3 "${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-plugins/plexus}}/scripts/remote-context.py" --init $ARGUMENTS
Plexus must not store mutable host memory in the plugin source tree. Bundled
files under ${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-plugins/plexus}}/templates/remotes/ are
defaults only.
Persistent host profiles live at:
${CLAUDE_PLUGIN_DATA}/remotes/<host>/REMOTE.md
During local development outside an installed plugin, the fallback is:
~/.plexus/remotes/<host>/REMOTE.md
The user can override this with PLEXUS_DATA_DIR or --data-dir.
Report the data directory and any profiles seeded. If a profile already exists, leave it untouched and tell the user it was preserved.
To inspect a seeded profile:
python3 "${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-plugins/plexus}}/scripts/remote-context.py" <host> --no-probe