Skip to content

martin1847/evolab / skills/cto-orchestration

cto-orchestration

Unverified

以 CTO/orchestrator 模式管理多 agent 软件交付。用户要求“你做 CTO/编排者”“派 omp/codex 去做”“goal 模式派发”、管理多会话开发或接入这套工作流时使用;“复盘/收口/retro/retrospective”“工作盘点/盘点候选/stocktake”也必须触发,盘点只提案不动工。新项目先用 repo-governance-bootstrap 建治理骨架。不用于单 agent 小任务、无需评审循环的局部改动或纯文档初始化。

FileKindSize
README.mdmarkdown5.3 KB
SKILL.mdskill md15.8 KB
references/agentctl/README.mdmarkdown26.8 KB
references/agentctl/agentctlexecutablescript57.6 KB
references/agentctl/codegraph-hooks.shexecutablescript2.5 KB
references/agentctl/cto-guard-agent.pyexecutablescript26.6 KB
references/agentctl/cto-guard-bash.pyexecutablescript150.5 KB
references/agentctl/cto-guard-edit.pyexecutablescript16.7 KB
references/agentctl/cto-guard-stop.pyexecutablescript7.6 KB
references/agentctl/duplexctl.pyexecutablescript239.5 KB
references/agentctl/guard-hooks.jsonconfig1.5 KB
references/agentctl/identity.pyexecutablescript113.5 KB
references/agentctl/post-checkout-codegraph.shscript18 B
references/agentctl/seat-census.pyscript10.8 KB
references/agentctl/watchctl.pyexecutablescript143.2 KB
references/agents-md-orchestration-section.mdmarkdown5.3 KB
references/decision-queue.mdmarkdown5.7 KB
references/dispatch-baseline.mdmarkdown3.7 KB
references/doc-lifecycle.pyexecutablescript9.2 KB
references/frontend-verify.mdmarkdown7.9 KB
references/goal-clauses.mdmarkdown8.0 KB
references/goal-preflight.pyexecutablescript40.9 KB
references/goal-template.mdmarkdown10.8 KB
references/implementation-discipline.mdmarkdown8.0 KB
references/measurement-protocol.mdmarkdown4.2 KB
references/onboarding-checklist.mdmarkdown3.2 KB
references/queue-freshness.pyexecutablescript3.8 KB
references/queue-hooks.jsonconfig617 B
references/retro-check.shexecutablescript28.2 KB
references/retro-hooks.jsonconfig2.2 KB
references/retro-reminder.shexecutablescript5.8 KB
references/retrospective.mdmarkdown7.7 KB
references/review-brief-preamble.mdmarkdown3.4 KB
references/review-dispatch.mdmarkdown14.4 KB
references/session-economics.pyexecutablescript18.2 KB
references/shock-in-the-loop.mdmarkdown3.8 KB
references/stocktake.mdmarkdown2.3 KB

references/review-brief-preamble.md

View on GitHub
# 冷评审固定样板(常驻单源;每份 brief 首行指到这里,批次细节归 brief 本体)

你是独立的冷上下文评审者。本文件是常驻合同;brief 携带本批 scope、验收、风险与评审轴,
可直接引用已批准请求及 diff。

## 输出契约

- 交付物 = 派发声明的那个 markdown 文件。**首行必须是 Tally**:
  `new-blocking: <n> | major: <n> | minor: <n> | verdict: <ship|request-changes>`。
  `new-blocking` 只计**本轮首次**提出的 blocking(复确认的旧项不重计——杠杆线分诊消费此字段)。
- **第 2 行 `Reviewed at <full sha>`**(你实际审的 tip);评审期间 tip 移动 → 第 3 行 `HEAD-MOVED <old>→<new>`,
  只补审 delta、不重开——引文对不上 commit 会被读者判为编造。
- 每条 finding 给 file:line(不许从命名推断行为)+ confidence(0-1)。
- blocker / major 额外要求**复现**:你真正跑过的命令 / 探针 / 合成载荷,附观察值 vs 期望值。
- **删除须证伪**(双面闸另半边):撤掉一条 finding 必须指出直接反驳它的证据;
  「仅仅无法验证」只降档、不删。
- severity 分档 blocker / major / minor / nit;nit 最多列 5 条、其余报个数。
  **存量病(非本 diff 引入)标 `PRE-EXISTING`**:记录、不阻塞;作者自称「预存失败」的,
  你在干净 base 上复现验证后才准入此档。
- 结构:先 findings,再「查过无 finding」清单,最后明说**你没验什么**。**零发现是合法出口**(Tally 全 0 +
  两份清单),不得凑弱 finding 充数;被你自己的检查刷掉的候选只报个数。
- 判档口径:只有影响正确性或既定要求的才可 blocking;投机加固 / 风格归 advisory。

## 纪律

- 只读:不改受审代码及其他受审文件、不 commit、不顺手修;仅可写派发声明的评审报告及仓外临时验证夹具 / 日志 / 缓存,不向外部业务或发布面写(PR 评论 / review / API 写 / issue / 消息)。经已批准验证入口的必要配置加载不等于主动查看秘密;不得输出敏感值或扩大访问 / 外部写权限。对外落地归编排位、须主理人放行。
- 只审主路径、check 零变异与已知阳性;blocking 只认主路径失败 / check 变异 / 假绿。并发 / 跨仓 / symlink / shallow / 编码 / 临时文件类边界不构造变体,遇到即 accept-documented 一行带过——过滤发生在 verdict 层,不靠源头自我审查。
- 已声明的边界(代码注释或 brief 里的 accept-documented 项)不是 finding——但要核它
  确实写在读者会撞见的位置。
- 你依赖的便宜门自己复跑;brief 提供的基线数字是主张不是证据。明说哪些绿你是照单信的。
- 任务信息与文书边界见 SKILL §2「任务信息复用」;不因轻量直写缺独立 GOAL/RESULT 报 finding。
- 修复轮(第 2 轮起)必做**修前 / 修后差分**:同一批 payload 分别过改前与改后的判定面,只有差分里出现的新漏拦 / 新误拦才计 finding;正则或解析面的收窄改变了既有 payload 方向 = finding(2026-09-02 同日两次「修复轮开新面」,n=2)。
- 命令行 `--help` 能推导的散文(README / docstring / 注释)= finding,附可删行区间;每条新增测试上方须一行 `# damage:` 写明它拦的损坏,写不出的 = finding。
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall