takeover
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseTakeover
接管
Finish the original goal from inherited work while preserving ownership,
contributor credit, and newer changes.
完成继承工作的原始目标,同时保留所有权、
贡献者署名和较新的更改。
Operating contract
操作契约
Shared by every DecisionNerd/dev-skills skill. Canonical copy: .
handbook/concepts/14-operating-contract.md- Define done first. Before using tools, write the finish line in one or two lines: acceptance criteria (existing issue AC, BDD scenarios, tests, or contract; otherwise propose them and where they should live) and the evidence that will prove them. Re-check it before reporting done. Never report done on unverified work.
- Requested scope sets the finish line. A question ("is it ready?", "why is it broken?", "what next?") ends with the answer and a line naming the exact next invoke. An outcome request ("fix", "finish", "land", "#42") continues through the chain (diagnose → fix → test → check-readiness → merge-it) until the outcome or a real blocker. Do not end a turn with "Do you want me to…?" for in-scope, in-repo work.
Next: - Stop only for real blockers. Stop and ask only when you cannot continue without the user, or before: deleting data or unmerged work, force-push or history rewrite, changing anything outside this repository (GitHub objects, deployments, live data, production or paid resources, external services), or leaving the requested scope, unless the user's request already named that exact action. Keep the harness's permission prompts for risky commands. Otherwise keep going and put status notes in the same message as the next action.
- Ask well, once. For a genuine question use the harness's structured question tool when it has one (Claude Code: ; Codex:
AskUserQuestionwhen the current mode supports it; T3 Code: therequest_user_inputtool) with concrete options; otherwise plain text with numbered options. Treat the answer as settled; do not re-open earlier verdicts, plans, or answers unless asked.question - Fan out when work is parallel. Use subagents for independent reads (repo survey, evidence gathering, per-option research, per-area audits) and independent verification (a reviewer that did not write the change). Writes stay single-owner per path set and sequential. Brief every child with goal, done-when, constraints, must-not, and return shape; verify each result before consolidating. Use Claude Code's tool only when orchestrating many subagents truly needs it; it is expensive. T3 Code: its delegated subagents — with optional worktree isolation for independent verification — cover this without the
Workflowtool.Workflow - Pick the model tier per child; defer to routing config. If the harness or user config already routes subagents, follow it and do not pass a model. Otherwise pick a tier per child: mechanical search or inventory → fast/cheap; implementation and evidence gathering → mid; planning, review, adversarial verification → top. Tier names differ per harness (Claude Code: /
haiku/sonnetoropus; T3 Code: inherit by default or pick from its live provider/model catalog). Set the choice with the harness's spawnfableparam or agent frontmattermodel(per-harness details:model:). Where the harness cannot choose, children inherit or the harness picks; say which in the status note.skills/agents/references/sub.md - Keep a checklist on long runs. For more than about five steps or work that crosses skills, keep at the repo root and tick items as they finish. Do not commit it unless the repo already tracks one.
TASKS.md - Close every run with three headings. (the one genuine question or blocker, else "none");
Blocked on me(files, commits, GitHub objects, deploys, else "nothing");Changed(evidence, verdict, andFound).Next: <exact invoke>
由每个 DecisionNerd/dev-skills skill 共享。规范副本:。
handbook/concepts/14-operating-contract.md- 先定义完成标准。 在使用工具前,用一两行写明终点:验收标准(现有 issue AC、BDD 场景、测试或契约;否则应提出这些标准及其存放位置)以及能够证明它们的证据。报告完成前重新检查。绝不在未经验证的工作上报告完成。
- 请求范围决定完成终点。 对于问题(“ready 了吗?”、“为什么坏了?”、“下一步是什么?”),应以答案和 行结束,并注明下一次 invoke 的准确内容。对于结果请求(“修复”、“完成”、“合入”、“#42”),应沿链路持续执行(诊断 → 修复 → 测试 → 检查就绪状态 → merge-it),直至达成结果或遇到真正的阻塞。对于范围内的仓库内工作,不得以“要我继续做什么吗?”结束回合。
Next: - 仅在遇到真正阻塞时停止。 只有在缺少用户就无法继续,或即将执行以下操作时,才停止并询问:删除数据或未合并的工作、force-push 或重写历史、修改本仓库之外的任何内容(GitHub objects、deployments、live data、production 或 paid resources、external services),或偏离请求范围;除非用户请求已明确指定该操作。保留 harness 对高风险命令的权限提示。除此之外应继续执行,并在同一条消息中附上状态说明和下一步操作。
- 只进行一次高质量询问。 对于真正的问题,当 harness 提供了结构化提问工具时,使用该工具(Claude Code:;Codex:在当前模式支持时使用
AskUserQuestion;T3 Code:使用request_user_input工具),并提供具体选项;否则使用带编号选项的纯文本。将回答视为已确定;除非用户要求,不要重新讨论此前的结论、计划或答案。question - 并行工作时进行 fan out。 使用 subagent 执行独立的读取操作(仓库调查、证据收集、按选项研究、按区域审计)和独立验证(由未编写变更的审查者执行)。对于每组路径,写入操作保持单一所有者并顺序执行。向每个子任务说明目标、完成条件、约束、禁止事项和返回结构;整合前验证每个结果。只有在确实需要编排大量 subagent 时才使用 Claude Code 的 工具;该工具成本较高。T3 Code:其委派的 subagent 可完成此工作,并可选择使用 worktree 隔离进行独立验证,而无需
Workflow工具。Workflow - 为每个子任务选择 model tier;遵循路由配置。 如果 harness 或用户配置已经为 subagent 设定路由,则遵循该配置且不要传入 model。否则,为每个子任务选择 tier:机械式搜索或清单 → fast/cheap;实现和证据收集 → mid;规划、审查、对抗性验证 → top。各 harness 的 tier 名称不同(Claude Code:/
haiku/sonnet或opus;T3 Code:默认继承,或从其当前 provider/model catalog 中选择)。通过 harness 的 spawnfable参数或 agent frontmattermodel设置选择(各 harness 的详细信息参见model:)。当 harness 无法选择时,由子任务继承或由 harness 选择;在状态说明中指出实际方式。skills/agents/references/sub.md - 长时间运行要保留 checklist。 当工作超过约五个步骤或跨越多个 skill 时,在仓库根目录维护 ,并随着完成逐项勾选。除非仓库已经跟踪该文件,否则不要提交它。
TASKS.md - 每次运行都以三个标题收尾。 (唯一真正的问题或阻塞项,否则为“none”);
Blocked on me(文件、提交、GitHub objects、部署,否则为“nothing”);Changed(证据、结论和Found)。Next: <exact invoke>
When to use
何时使用
takeover <PR|branch|agent-thread>- Continue another agent's implementation or accept an explicit handoff.
A takeover does not itself authorize merging, closing the source PR, deleting
branches, or replacing another active agent's checkout.
takeover <PR|branch|agent-thread>- 继续另一个 agent 的实现,或接受明确的交接。
接管本身并不授权合并、关闭源 PR、删除分支,
或替换另一个活跃 agent 的 checkout。
Instructions
指令
1. Reconstruct the handoff
1. 重建交接上下文
Read the source PR or thread, linked issues, reviews, commits, and later user
corrections. In T3 Code, read a named thread with before relying
on its contents; use its returned link when referring to it.
t3_thread_readResolve the actual repository, base, source head SHA, branch/worktree ownership,
and uncommitted work. State the original goal, the inherited state, and the
requested finish line: local implementation, updated PR, ready for human merge,
or merged work. Treat prior summaries and green checks as leads to verify.
读取源 PR 或线程、关联 issues、reviews、commits,以及后续的用户修正。在 T3 Code 中,依赖线程内容之前,先用 读取指定线程;提及时使用其返回的链接。
t3_thread_read确定实际仓库、base、源 head SHA、分支/worktree 所有权和未提交的工作。说明原始目标、继承状态和请求的完成终点:本地实现、更新后的 PR、准备好供人工合并,或已合并的工作。将此前的摘要和绿色检查结果视为需要验证的线索,而非结论。
2. Establish write ownership
2. 建立写入所有权
Inspect worktree attachment and activity before writing. Never take over an
active agent's branch or worktree without an explicit handoff. Preserve dirty
and unrelated work; do not reset, stash, or move it to make the checkout usable.
Use an owned continuation branch/worktree when safe ownership cannot be
established, following the harness's worktree rules.
For a replacement PR, carry forward the original commits with authorship intact
and add fixes separately. Respect an explicitly requested in-place or stacked
continuation. Do not open a duplicate PR or mutate the source PR merely because
a local continuation exists.
写入前检查 worktree 关联和活动情况。未经明确交接,绝不接管活跃 agent 的分支或 worktree。保留脏工作区和无关工作;不要为了使 checkout 可用而 reset、stash 或移动它。当无法安全确定所有权时,使用自有 continuation branch/worktree,并遵循 harness 的 worktree 规则。
对于替代 PR,在保持 authorship 原样结转原有 commits,并将修复单独添加。尊重明确要求的原地(in-place)或 stacked continuation。不要仅仅因为存在本地 continuation 就打开重复 PR 或修改源 PR。
3. Reassess and finish the same goal
3. 重新评估并完成同一目标
Compare the source work with its freshly fetched intended base. Check whether
the original failure still reproduces and whether newer work already solves it.
If is installed, use it for this assessment with the continuation
branch as the write target; do not let it update the source branch inadvertently.
Otherwise inspect base changes, conceptual conflicts, and the final diff directly.
modernizePreserve intended behavior while replacing stale implementation choices. Fix
accepted defects and review findings within the original goal. If the goal is
already satisfied, report the evidence without creating redundant changes.
Run focused checks and realistic workflow verification appropriate to the change;
distinguish fixtures, local results, CI, and live behavior.
Before any source-branch update or replacement PR, re-read the source PR/head and
account for new commits or corrections. Reconcile concurrent work instead of
overwriting it. A stale handoff never authorizes a stale-head push.
将源工作与刚获取的目标 base 进行比较。检查原始故障是否仍可复现,以及较新的工作是否已经解决该问题。如果已安装 ,使用它进行评估,并将 continuation branch 作为写入目标;不要让它无意中更新源 branch。否则,直接检查 base 更改、概念冲突和最终 diff。
modernize在替换过时的实现选择时,保留预期行为。在原始目标范围内修复已接受的缺陷和 review findings。如果目标已经满足,则报告证据,不创建冗余更改。运行与变更相适应的聚焦检查和真实工作流验证;区分 fixtures、本地结果、CI 和 live behavior。
在更新源 branch 或创建替代 PR 前,重新读取源 PR/head,并纳入新的 commits 或修正。协调并行工作,而不是覆盖它。陈旧的交接绝不授权执行 stale-head push。
4. Preserve credit and deliver
4. 保留署名并交付
Keep existing author identities and co-author trailers. Credit contributors and
link the source PR in a continuation PR's description. When squash merging is
authorized, preserve human author/co-author credit in the merge commit using
identities verified from commits or contributor records; do not guess emails.
Model attribution does not replace contributor credit.
In T3 Code, link each PR taken over, created, or pushed to with
as the next tool call once the action/PR is resolved. Include
every stack layer and report linking failures.
link_pull_requestUse available delivery skills for the requested finish line:
for a PR, for monitoring, for human merge, or
for an authorized merge. Missing companion skills are not a blocker:
perform the same scoped checks and handoff directly. Keep a ready-only request
ready-only through every handoff. Creating a PR alone is not a monitoring result.
For a ready-only delivery without companion skills, inspect and disable this
PR's unattended merging under that request, or report a blocker before pushing.
Verify checks/reviews on the final head and hand back the open PR. If no supported
wait mechanism exists, report that limitation rather than claim ongoing monitoring.
pulls createpulls watchmerge-it preparemerge-itDo not close the source PR, merge, force-push, or delete inherited work without
authorization for that action. Preserve branch protection and repository policy.
保留现有 author identities 和 co-author trailers。在 continuation PR 的描述中署名贡献者并链接源 PR。获得 squash merge 授权时,使用从 commits 或贡献者记录中验证的身份,在 merge commit 中保留 human author/co-author 署名;不要猜测邮箱。模型署名不能替代贡献者署名。
在 T3 Code 中,一旦接管、创建或推送的 PR 已确定,就将 作为下一次工具调用,关联每个 PR。包含堆叠的每一层,并报告关联失败。
link_pull_request根据请求的完成终点,使用可用的交付 skills:创建 PR 使用 ,监控使用 ,为人工合并做准备使用 ,已授权合并使用 。缺少配套 skill 并非阻塞项:直接执行相同的范围检查和交接。所有交接都必须保持“仅准备就绪”(ready-only)请求仍为 ready-only。仅创建 PR 不等于完成监控。对于没有配套 skill 的 ready-only 交付,检查并按照请求禁用此 PR 的无人值守合并,或在推送前报告阻塞项。在最终 head 上验证 checks/reviews,并把开放的 PR 交还。如果没有受支持的等待机制,应报告该限制,而不是声称会持续监控。
pulls createpulls watchmerge-it preparemerge-it未经相应操作授权,不要关闭源 PR、合并、force-push 或删除继承的工作。保留 branch protection 和 repository policy。
Output
输出
Report the source link/head, inherited and changed work, proof, how credit was
preserved, the continuation PR/head when present, and remaining decisions.
Distinguish completed work from claims inherited but not independently verified.
报告源链接/head、继承和变更的工作、证明、署名保留方式、存在时的 continuation PR/head,以及剩余决策。区分已完成的工作与继承但未独立验证的说法。
Source
来源
Adapted from Theo Browne's takeover skill
(MIT). Upstream notice: LICENSE.
改编自 Theo Browne 的 takeover skill(MIT)。上游声明:LICENSE。