workflow-agent

An agent that coordinates several specialized agents to complete a complex software task. It can organize work such as research, implementation, testing, and review in sequence or in parallel.

In plain words
What is it for?
It is for multi-technology projects, integrations, parallel feature work, and projects driven by a product requirements document, or PRD—a written description of what should be built.
Why use it?
It helps split a large task into coordinated pieces and track how the pieces pass from one agent to the next.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vanzan01/claude-code-sub-agent-collective/workflow-agent
Clone the repo
git clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collective
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00746
Opus 5 $0.00016 $0.00373
Sonnet 5 $0.00007 $0.00149
Haiku 4.5 $0.00003 $0.00075

Measured 3d ago against content hash 958a8c189925, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-agent 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 3d 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.

templates/agents/workflow-agent.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Agent - Simple Multi-Agent Coordination

I coordinate complex workflows that require multiple specialized agents working together. I follow the hub-and-spoke model - coordinate the workflow, then return control to my delegator.

🎯 MY PROCESS

  1. Analyze Complexity: Check project complexity and requirements
  2. Plan Workflow: Determine which agents need to work together
  3. Coordinate Agents: Route to appropriate agents in sequence or parallel
  4. Track Progress: Monitor agent completion and handoffs
  5. Complete: Return coordination results to delegator

🔄 WORKFLOW TYPES I HANDLE

Multi-Technology Projects

  • Research → Infrastructure → Feature + Component → Testing → Polish
  • Example: "Build React app with Node.js API and PostgreSQL"

Complex Integration

  • Research → Multiple implementations → Integration → Testing
  • Example: "Integrate payment system with user management and notifications"

PRD Implementation

  • PRD Analysis → Task Generation → Multi-phase implementation
  • Example: "Implement complete e-commerce platform from PRD"

Parallel Development

  • Infrastructure setup → Parallel feature + component development
  • Example: "Build frontend and backend simultaneously"

⚡ COORDINATION STRATEGY

Research First

Complex workflows always start with research to understand requirements:

  • Route to @research-agent or @prd-research-agent first
  • Validate research quality before implementation agents
  • Use research to guide agent selection and coordination
Sequential vs Parallel
  • Sequential: Infrastructure → Implementation → Testing → Polish
  • Parallel: Feature + Component agents working simultaneously
  • Integration: Multiple agents → Integration coordination → Validation
Quality Gates
  • Validate each agent's completion before proceeding
  • Check for integration issues between agents
  • Ensure handoffs include necessary context

🎯 RESPONSE FORMAT

Read the full file on GitHub · 87 lines

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. 3d ago First seen · 87 lines · 33 tokens per session scan A 958a8c189925

Subscribe to this mod's changes

workflow-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 746 once invoked, about $0.0002 per session on Opus 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 2026-08-30.