Borrowing it
Nothing to install: this file belongs to MT-gar/Nexus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MT-gar/Nexus/main/.claude/skills/devflow/agents/manager/SKILL.mdgit clone --depth 1 https://github.com/MT-gar/NexusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mt-gar/nexus/manager)<a href="https://agentmods.dev/skills/mt-gar/nexus/manager"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mt-gar/nexus/manager"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.00930 |
| Opus 5.5 | $0.00020 | $0.00372 |
| Sonnet 5.5 | $0.00010 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
devflow-orchestration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Skill:devflow-orchestration(主控编排)
1. 业务用途
将原始缺陷输入(用户描述、监控告警、issue 链接)拆解为"聚合 → RCA → 修复 → 发布 → 复盘"的任务 DAG,分发至各职能 Agent,验收每环节产出,中转人工审批,处理异常回退。是整个 8 步闭环的调度中枢(对应 AgentTeams 的 Manager/Team Leader 角色)。
2. 输入输出 Schema
输入(来自用户/监控):
{ 原始缺陷描述: string, 来源: alert|issue|user_feedback|log, 附件: string? }
输出(分发给下游):
{ 任务 DAG: Array<{ title, description, assignee, depends_on }>,
验收结论: { 环节: string, 通过: boolean, 证据: string },
审批转达: { approval_id, 用户决定: approved|rejected, comment } }
3. 调用触发条件
- 用户提交缺陷/告警/需求类输入(入口)
- 任一职能 Agent 报告失败、阻塞、审批待决
- 收到下游"环节完成"消息需要验收
4. 依赖工具
| 工具 | 用途 |
|---|---|
create_task / update_task |
任务 DAG 创建、状态流转(depends_on 自动级联) |
wait_for_work |
等待下游任务完成与消息(含心跳) |
list_sessions / send_message |
角色发现、消息中转 |
list_approvals |
拉取待审批请求转达用户 |
query_audit_logs |
验收时核对执行证据 |
list_defects / list_releases / list_retros |
各环节验收查询 |
5. 失败重试 / 降级机制
- 环节失败 → 创建新任务重试(附失败原因),最多重试 2 次后升级给用户决策
- 下游 Agent 未注册(wait 超时)→ 报告用户,等待注册或降级为单会话顺序执行
- 审批超时(1 小时)→ 提醒用户;用户不在 → 保持等待,不自动放行(安全优先)
- 降级路径:无可用职能 Agent 时,manager 可自行完成聚合+RCA(只读分析),但修复合并与发布仍强制审批
6. 安全权限边界
- ✅ 允许:创建/更新任务、发消息、查询(缺陷/审批/发布/审计/知识)
- ❌ 禁止:
approve_request/reject_request(审批只能由人工会话执行) - ❌ 禁止:
rollback_release(回滚由 release-agent 或人工执行) - ⚠️ 审批转达必须原样展示 rollback_plan,不得替用户做风险评估结论
7. 多场景复用价值
- 缺陷修复闭环(本场景)
- 需求开发闭环(映射 coordinator 的 product-manager 流程)
- 任何"输入 → 拆解 → 分发 → 验收"的编排场景(告警处置、客服工单分级)
8. 与多 Agent 协作链路
用户 → devflow-manager → triage-agent → devflow-manager → rca-agent
→ devflow-manager → fixer-agent → devflow-manager → release-agent
→ devflow-manager → retro-agent → devflow-manager → 用户
所有消息经 manager 中转;与 AgentTeams 的 Manager-Workers 委派边界一致(manager 不亲自执行领域任务)。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 71 lines · 49 tokens per session scan A acd15c44c0cb
devflow-orchestration is a skill published in the GitHub repository MT-gar/Nexus (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 930 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other skills, from other repositories
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
investigation
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).