Nexus: Skill for Claude Code

.claude/skills/devflow/agents/manager/SKILL.md

devflow-orchestration is a skill for Claude Code from MT-gar/Nexus. It costs 49 tokens per session (930 once invoked), scanned A, original, MIT.

A coordinator for a software-defect process that breaks an incoming report or alert into dependent jobs: collecting details, finding the cause, fixing it, releasing it, and reviewing the result. It assigns jobs to specialised agents and waits for approvals or failures.

In plain words
What is it for?
Use it to turn user reports, monitoring alerts, or issue links into a task graph, distribute the work, verify each stage, and coordinate retries, approvals, releases, and retrospectives.
Why use it?
It prevents a complex defect from being handled as one untracked conversation. Dependencies, checks, retries, human decisions, and fallback paths are kept in one workflow.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is MT-gar/Nexus's own configuration. It tells Claude Code how to work on Nexus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Nexus configures →

View source ↗ MT-gar/Nexus
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/MT-gar/Nexus/main/.claude/skills/devflow/agents/manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MT-gar/Nexus

Made for: Claude Code.

Wrote 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.

agentmods badge for devflow-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/mt-gar/nexus/manager/github.svg)](https://agentmods.dev/skills/mt-gar/nexus/manager)
Your own site
<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.

agentmods 80×15 button for devflow-orchestration

Your own site · 80×15
<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>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 1mo ago against content hash acd15c44c0cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/skills/devflow/agents/manager/SKILL.md · 71 lines

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)。

Changes

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.

  1. 1mo ago First seen · 71 lines · 49 tokens per session scan A acd15c44c0cb

Subscribe to this mod's changes

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.

Related

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.

Donchitos/Claude-Code-Game-Studios · 30 tokens

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.

backnotprop/pstack · 46 tokens

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.

Gentleman-Programming/gentle-ai · 57 tokens

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…

atlassian/atlassian-mcp-server · 116 tokens

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…

modu-ai/moai-adk · 86 tokens

investigation

Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).

me2resh/apexyard · 26 tokens