菜单
Run e2e tests relevant to the current changes. Selects `.feature` files based on `git diff`, runs `just test-quick`, and skips e2e when changes are server-only with no UI impact. Triggers on "run tests", "test this", "check if it works", "e2e", "test the changes".
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
Drive one AI agent from another through kolu's terminals: spawn a Claude Code / Codex / opencode session in a PTY, prompt it, watch the screen for its reply, read it, and prompt again. PRIMARY PATH: the kolu MCP server's tools (`lifecycle_create`/`lifecycle_sendInput` with named keys, the `wait_outputSettled`/`wait_agentState` done-signals, `screen_text`, the `terminals` resource) — configured in this repo's .mcp.json as `kolu mcp`. FALLBACK when the MCP is unavailable: the `kaval-tui`/`padi-tui` CLIs, same verbs, same discipline. Triggers on "drive another agent", "send a prompt to a terminal agent", "have one agent prompt another", "agent drives agent", "orchestrate agents in terminals", "make Claude drive Codex", "prompt the agent running in that terminal", or wiring a loop where one coding agent supervises another.
Running memory of the coordination rules for an orchestrator agent driving implementing agents on kolu terminals — authorization boundaries, the dispatch protocol (MCP-first via the kolu skill, with its TUI fallback), verification discipline, and how to communicate with the human. Load whenever coordinating a multi-agent campaign (dispatching briefs to agents in kolu PTYs, tracking their PRs, verifying their claims), or when acting as the coordinator in a padi/surface-style campaign. Triggers on "orchestrate the agents", "coordinate the campaign", "dispatch to the agents", "act as coordinator", or driving multiple implementing agents from one supervising session.
Running memory of the coordination rules for an orchestrator agent driving implementing agents on kolu terminals — authorization boundaries, the dispatch protocol (MCP-first via the kolu skill, with its TUI fallback), verification discipline, and how to communicate with the human. Load whenever coordinating a multi-agent campaign (dispatching briefs to agents in kolu PTYs, tracking their PRs, verifying their claims), or when acting as the coordinator in a padi/surface-style campaign. Triggers on "orchestrate the agents", "coordinate the campaign", "dispatch to the agents", "act as coordinator", or driving multiple implementing agents from one supervising session.
Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex critiques the current diff and Claude (author) fixes/disputes, looping until they agree, and the trail is committed + posted to the PR. `answer` — Claude and codex each answer a freeform prompt, then cross-check until they agree, and a unified answer is returned. The debate runs over a LIVE codex session in a split terminal beside you (driven per the /kolu skill), not a headless workflow. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex critiques the current diff and Claude (author) fixes/disputes, looping until they agree, and the trail is committed + posted to the PR. `answer` — Claude and codex each answer a freeform prompt, then cross-check until they agree, and a unified answer is returned. The debate runs over a LIVE codex session in a split terminal beside you (driven per the /kolu skill), not a headless workflow. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
| name | test |
| description | Run e2e tests relevant to the current changes. Selects `.feature` files based on `git diff`, runs `just test-quick`, and skips e2e when changes are server-only with no UI impact. Triggers on "run tests", "test this", "check if it works", "e2e", "test the changes". |
Run e2e tests scoped to the current branch's changes.
git diff master...HEAD --name-only to list files changed on this branch..feature files under packages/tests/features/. Use file names, component names, and domain knowledge to find the right scenarios.packages/client/src/, packages/tests/, or packages/common/src/ — run the matching feature files.packages/server/src/ only) with no UI impact — unit tests may suffice. Skip e2e if no relevant scenarios exist.just test-quick builds the client and spawns a server: that is heavy work, and it goes on an ephemeral pu box (see /pu / /evidence) any time systemctl --user is-active kolu is active (the normal case). A pile-up of local e2e runs OOM-SIGKILLed production kolu.service beside this command before — "fast" is not "safe to run beside production." Apply /dev-server §0's local-vs-pu venue gate before invoking it, and run locally only when production is inactive here.just test-quick features/foo.feature (or just test-quick features/foo.feature:42 for a single scenario).just test-quick is fast — no nix build, no separate dev server needed — but fast is not local-by-default: see step 4.