.cursor/.agents/skills/dmux-workflows/SKILL.md
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
npx skillsauth add LUAgam/stage-harness dmux-workflowsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.
dmux is a tmux-based orchestration tool that manages AI agent panes:
n to create a new pane with a promptm to merge pane output back to the main sessionInstall: npm install -g dmux or see github.com/standardagents/dmux
# Start dmux session
dmux
# Create agent panes (press 'n' in dmux, then type prompt)
# Pane 1: "Implement the auth middleware in src/auth/"
# Pane 2: "Write tests for the user service"
# Pane 3: "Update API documentation"
# Each pane runs its own agent session
# Press 'm' to merge results back
Split research and implementation into parallel tracks:
Pane 1 (Research): "Research best practices for rate limiting in Node.js.
Check current libraries, compare approaches, and write findings to
/tmp/rate-limit-research.md"
Pane 2 (Implement): "Implement rate limiting middleware for our Express API.
Start with a basic token bucket, we'll refine after research completes."
# After Pane 1 completes, merge findings into Pane 2's context
Parallelize work across independent files:
Pane 1: "Create the database schema and migrations for the billing feature"
Pane 2: "Build the billing API endpoints in src/api/billing/"
Pane 3: "Create the billing dashboard UI components"
# Merge all, then do integration in main pane
Run tests in one pane, fix in another:
Pane 1 (Watcher): "Run the test suite in watch mode. When tests fail,
summarize the failures."
Pane 2 (Fixer): "Fix failing tests based on the error output from pane 1"
Use different AI tools for different tasks:
Pane 1 (Claude Code): "Review the security of the auth module"
Pane 2 (Codex): "Refactor the utility functions for performance"
Pane 3 (Claude Code): "Write E2E tests for the checkout flow"
Parallel review perspectives:
Pane 1: "Review src/api/ for security vulnerabilities"
Pane 2: "Review src/api/ for performance issues"
Pane 3: "Review src/api/ for test coverage gaps"
# Merge all reviews into a single report
For tasks that touch overlapping files:
# Create worktrees for isolation
git worktree add ../feature-auth feat/auth
git worktree add ../feature-billing feat/billing
# Run agents in separate worktrees
# Pane 1: cd ../feature-auth && claude
# Pane 2: cd ../feature-billing && claude
# Merge branches when done
git merge feat/auth
git merge feat/billing
| Tool | What It Does | When to Use | |------|-------------|-------------| | dmux | tmux pane management for agents | Parallel agent sessions | | Superset | Terminal IDE for 10+ parallel agents | Large-scale orchestration | | Claude Code Task tool | In-process subagent spawning | Programmatic parallelism within a session | | Codex multi-agent | Built-in agent roles | Codex-specific parallel work |
m to read output.brew install tmux (macOS) or apt install tmux (Linux).development
在 generate-test-cases 阶段之后执行,逐个验证测试用例并在失败时修复项目代码、重新编译部署、再次验证, 直到通过或达到最大修复次数。覆盖 UI / API / API+UI / 性能测试四个维度,UI 测试通过浏览器真实模拟用户操作并截图, API 测试根据项目代码生成可执行的接口脚本,性能测试调用现有性能/质量技能全量执行。 涉及真实用户登录信息(如手机号+验证码、账号密码、JWT)时必须中断要求用户提供,禁止编造无效凭证。 所有 case 状态变更必须通过 e2e-case-tracker.sh 脚本持久化,确保中途崩溃可恢复、无 case 遗漏。
development
# SKILL: e2e > **核心原则**: > 1. 测试范围跟着本次变动走。后端接口改了,对应的前端流程必须做联调验证;与本次需求无关的功能不测。对于涉及算法、转换准确率等质量敏感型需求,需额外生成专项质量测试。 > 2. **覆盖完整性优先于执行便利性**。不得以"链路复杂"、"需要外部依赖"为由跳过本次变动相关的用例;凡是受变动影响的接口和 UI 流程,都必须生成真实调用/操作用例。 > 3. **UI 测试必须模拟真实用户操作**(定位元素、点击、键入、等待渲染、断言可见文本/状态)。**禁止**将 UI 套件退化为浏览器上下文里的 `page.evaluate(fetch(...))` API 验证——那只是把 API 测试换了执行环境,没有额外价值,不算 UI 测试。 > 4. **通用性**:本 skill 不假设具体业务域,所有规则均以抽象变动面(文件、接口、页面、用户动作)为单位组织,不针对任何特定项目的数据库/领域词汇。 > 5. **E2E 套件必须验证运行时行为**。严禁把"读取源码/配置文件并做字符串/结构匹配"的检查封装成独立 E2E 套件——这类检
tools
# SKILL: deploy ## CLI Bootstrap 在执行任何 `harnessctl` 命令前,先解析本地 CLI 路径: ```bash if [ -z "${HARNESSCTL:-}" ]; then candidates=( "./stage-harness/scripts/harnessctl" "../stage-harness/scripts/harnessctl" "$(git rev-parse --show-toplevel 2>/dev/null)/stage-harness/scripts/harnessctl" ) for candidate in "${candidates[@]}"; do if [ -n "$candidate" ] && [ -x "$candidate" ]; then HARNESSCTL="$candidate" break fi done fi test -n "${HARNESSCTL:-}" && test -x "$H
tools
# SKILL: build ## CLI Bootstrap 在执行任何 `harnessctl` 命令前,先解析本地 CLI 路径: ```bash if [ -z "${HARNESSCTL:-}" ]; then candidates=( "./stage-harness/scripts/harnessctl" "../stage-harness/scripts/harnessctl" "$(git rev-parse --show-toplevel 2>/dev/null)/stage-harness/scripts/harnessctl" ) for candidate in "${candidates[@]}"; do if [ -n "$candidate" ] && [ -x "$candidate" ]; then HARNESSCTL="$candidate" break fi done fi test -n "${HARNESSCTL:-}" && test -x "$HA