菜单
Apply the latest kit release on this machine — updates the my-dotclaude marketplace entry and both plugins, then reminds you to restart Claude Code. Use for "/update-kit", "update the kit", "apply latest kit release".
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。
基于 SOC 职业分类
Run one task through the plan→build→review pipeline — a Step-0.5 classify-task call routes the planner/implementer/reviewer models to the task's complexity tier, then the plan is written (planner subagent or inline), the implementer builds it in an isolated worktree, the my-review agent reviews the diff, and findings route by severity (low→issues, medium→triaged fix-list, high→collective replan, critical→own cycle). For single tasks not worth slicing into an issue graph. Use for "/pipeline <issue#|task>", "pipeline this".
Deep, security-weighted review of your changes or a PR — routes the reviewer model to the change's complexity (opus by default; fable for a complex diff, on ask), then spawns the my-review agent (xhigh reasoning) on that model. Read-only, report-only. Use for "/my-review", "/my-review <PR#>".
Classify one task or issue into a complexity tier — trivial, standard, or complex — and emit that tier plus a rationale; consumers resolve the tier's {model, effort} roster via the plugin's resolve-tier.sh. Grounds the call by fanning out 1–3 Explore subagents over the touched codebase areas, then asks you to confirm or override. Use for "/classify-task <issue#|brief>", "classify this task".
Run N rounds of the autonomous issue-solving loop — pick the ready set (blockers closed, skip hitl), fan out parallel implementers in isolated git worktrees, hand the completed branches to a merger that merges in dependency order and resolves conflicts under the done-check, close finished issues, then a reviewer files blocking follow-ups. Use for "/orchestrate", "run the loop", "build the ready issues".
Check whether the plan(s)/PRD(s)/issue-slice(s) under discussion still match the decisions made in this session — a sonnet subagent reads the current session log, later decisions win, and reports drift read-only. Use for "/verify-plan", "does my plan still match what we decided?".
Capture the just-approved plan after exiting plan mode and hand it to a fresh session — write the plan to a file plus the resume pointer the workflow plugin reads, then tell me to /clear and send `go` to execute it. Use for "/handoff-plan", "hand off this plan".
| name | update-kit |
| description | Apply the latest kit release on this machine — updates the my-dotclaude marketplace entry and both plugins, then reminds you to restart Claude Code. Use for "/update-kit", "update the kit", "apply latest kit release". |
| argument-hint | |
| model | inherit |
| allowed-tools | Bash |
Apply the latest kit release on this machine. No arguments needed.
Locate the backing script — it lives at
${CLAUDE_PLUGIN_ROOT}/scripts/update-kit.sh.
Run it with Bash:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/update-kit.sh"
The script issues three claude CLI calls in order:
claude plugin marketplace update my-dotclaudeclaude plugin update personal-toolsclaude plugin update workflowIt then refreshes the status line, which is not plugin payload: the
marketplace update above also refreshes Claude Code's local copy of the repo
(a git clone for a GitHub install, the live checkout for a directory
install), so the script reads that location from known_marketplaces.json
and reuses setup/lib/common.sh's installer to copy the new
global/statusline.py into ~/.claude/ and merge the settings.json
wiring — backing up the old files first. A refresh failure is non-fatal: the
plugin update still succeeded.
Report the result. If the script exits non-zero, surface the error and
tell the user to check their claude CLI installation. If it exits 0, confirm
that the kit was updated and remind them to restart Claude Code so the new
versions take effect.