Full product lifecycle plugin: define Vision/Mission/Core → generate workplan → execute with reviewer agents → synthesize deliverables → maintain.
Use to start the dispatcher loop — every task is executed by a worker agent then validated by a domain-expert reviewer agent before being marked done. Requires at least one pending task. Also triggers when the user says "start building", "run the dispatcher", "execute the workplan", or "start the dev loop". Pass --stop to stop a running dispatcher.
Use to initialize workflow-kit in any project with a guided step-by-step wizard. Defines Vision, Mission, Core, audits the system, configures LLMs, and sets lifecycle state to 'define'. Also triggers when the user says "set up workflow-kit", "define the product", "start a new project", or "configure my dev loop".
Use to set up and run scheduled maintenance jobs after a product is approved. Suggests jobs based on product type and schedules them via cron. Also triggers when the user says "set up maintenance", "keep the product updated", "schedule recurring checks", or "monitor the product ongoing".
Use to open the full live dashboard — Rich TUI in the terminal or web dashboard at localhost:7860. Also triggers when the user says "show live progress", "open workflow dashboard", "watch the dispatcher", or "monitor in browser". Pass --web for browser mode.
Use to generate a structured workplan — objectives and tasks — from workflow/product.md. Requires init to have run first (phase must be 'define' or 'plan'). Also triggers when the user says "generate my workplan", "plan the project", "create tasks from the product definition", or "what should the agent work on".
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A full product lifecycle plugin for Claude Code, Codex CLI, OpenCode, and Gemini CLI.
Define your product's Vision, Mission, and Core → generate a structured workplan → execute with mandatory domain-expert reviewer agents → synthesize deliverables → maintain.
The product can be anything: a webapp, a research paper, a library, an API, an article, a dataset. The workflow adapts automatically.
Everything needs a reviewer. No task is complete until a domain-expert reviewer agent has validated the output. The worker builds; the reviewer validates. These are separate agent processes — the reviewer is mandatory infrastructure, not optional.
The product defines the workflow. A webapp needs a code-reviewer and a devops reviewer. A research paper needs a researcher reviewer. An article needs an editor. workflow-kit detects your product type from your Vision and creates the right reviewer profiles automatically.
User is always the admin. Agents execute; you decide. You approve transitions between phases. Feedback at synthesis creates sub-tasks that loop back through execution — you never lose control of direction.
┌─────────┐ ┌──────┐ ┌─────────┐ ┌───────────┐ ┌──────────┐
│ DEFINE │───▶│ PLAN │───▶│ EXECUTE │───▶│ SYNTHESIZE│───▶│ MAINTAIN │
└─────────┘ └──────┘ └─────────┘ └───────────┘ └──────────┘
Vision + Objectives Agent+Reviewer Package + Scheduled
Mission + + Tasks pairs per task User review jobs
Core + ▲ │
System audit └──────────────────┘
feedback loop
State tracked in workflow/state.yaml. Each phase requires user approval to advance.
Use a different LLM provider for reviews than for worker tasks — eliminates sycophancy bias when a model reviews its own output.
# workflow.yaml
reviewers:
- endpoint: "https://api.anthropic.com/v1/messages"
api_key: "${ANTHROPIC_API_KEY}"
model: "claude-haiku-4-5-20251001"
Per-task override: add a "reviewer" field to any task JSON in workflow/tasks/pending/<id>.json to use a different reviewer for that specific task:
{
"task_id": "feat-007",
"reviewer": {
"endpoint": "https://api.openai.com/v1/chat/completions",
"api_key": "${OPENAI_API_KEY}",
"model": "gpt-4o"
}
}
If the dispatcher crashes mid-task (power loss, OOM, Ctrl+C), workflow-kit recovers automatically on next startup. File snapshots are written before each task begins and deleted when the task completes.
# Auto-detected on every startup. If dispatcher crashed mid-task:
python -m workflow_kit start # automatically recovers + retries interrupted task
python -m workflow_kit start --resume # same, explicit flag for clarity
Run multiple tasks concurrently. Tasks that share files are never run in parallel — conflict detection is automatic.
# workflow.yaml
settings:
max_parallel_tasks: 3 # run up to 3 tasks concurrently (default: 1)
Every completed task records timing, retry count, and reviewer pass/fail to .workflow/metrics.jsonl. View the dashboard via:
/workflow-kit:status → shows metrics dashboard
Or from CLI:
python -m workflow_kit status
| Skill | Phase | What it does |
|---|---|---|
/workflow-kit:init | define | Guided wizard: Vision/Mission/Core + system audit + LLM setup + reviewer profiles |
/workflow-kit:plan | plan | Orchestrator generates objectives + tasks from workflow/product.md |
/workflow-kit:execute | execute | Dispatcher runs tasks; spawns reviewer agent after each |
/workflow-kit:synthesize | synthesize | Packages output by product type; presents to user; handles feedback loop |
/workflow-kit:maintain | maintain | Creates and runs scheduled maintenance jobs |
/workflow-kit:status | any | Inline phase + dispatcher + task counts + reviewer results |
/workflow-kit:monitor | any | Live TUI or web dashboard |
# Step 1: add the marketplace (one time only)
claude plugin marketplace add Le-Xuan-Thang/workflow-kit
# Step 2: install the plugin
claude plugin install workflow-kit
Restart Claude Code. Skills available as /workflow-kit:init, /workflow-kit:plan, etc.
# Step 1: add the marketplace
codex plugin marketplace add Le-Xuan-Thang/workflow-kit
# Step 2: install the plugin
codex plugin add workflow-kit@Le-Xuan-Thang
npx claudepluginhub le-xuan-thang/workflow-kit --plugin workflow-kitv9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses