agent-workflows

A guide to coordinating multiple coding agents, where each agent handles a defined part of a larger task. It describes step-by-step, parallel, and fault-tolerant workflows.

In plain words
What is it for?
Use it to design workflows for feature development, codebase analysis, research, and other tasks that need several agents working in sequence or at the same time.
Why use it?
It helps break complex work into manageable pieces and clarifies how agents should pass results to one another. This reduces duplicated effort and confusion about responsibilities.

Agent for Claude Code

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/daffy0208/ai-dev-standards/agent-workflows
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,598 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 $0.00000 $0.03598
Opus 5 $0.00000 $0.01799
Sonnet 5 $0.00000 $0.00720
Haiku 4.5 $0.00000 $0.00360

Measured 3d ago against content hash 1fdd2850bad5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-workflows 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.

.claude/agents/agent-workflows.md · 754 lines

How it starts

The opening of the file, as written. The whole thing — 754 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Workflows & Coordination Patterns

How agents work together to accomplish complex tasks through proven coordination patterns.


Table of Contents

  1. Overview
  2. Basic Patterns
  3. Advanced Patterns
  4. Real-World Workflows
  5. Best Practices

Overview

Agents can be coordinated in various patterns to accomplish complex tasks more efficiently than single-agent approaches. This document catalogs proven coordination patterns and workflows.

Key Principles:

  • Separation of Concerns: Each agent has a clear responsibility
  • Loose Coupling: Agents communicate through well-defined interfaces
  • Composability: Patterns can be combined for complex workflows
  • Fault Tolerance: Workflows handle agent failures gracefully

Basic Patterns

1. Sequential Pattern

Structure:

Agent A → Agent B → Agent C

Description: Agents execute one after another, with each agent's output becoming the next agent's input.

When to Use:

  • Tasks have clear dependencies
  • Each step builds on previous results
  • Order matters

Example:

Workflow: Feature Implementation
1. Explore Agent (Medium) → Understand codebase
2. General-Purpose + frontend-builder → Design implementation
3. General-Purpose + testing-strategist → Add tests
4. Codex-Review-Workflow → Validate code

Advantages:

  • Simple to understand and implement
  • Clear data flow
  • Easy to debug

Disadvantages:

  • Slow (serial execution)
  • Blocked by any agent failure
  • No parallelization

2. Parallel Pattern

Structure:

        Agent B
       ↗
Agent A → Agent C
       ↘
        Agent D

Description: Multiple agents execute simultaneously on independent tasks, results aggregated at the end.

When to Use:

  • Tasks are independent
  • No dependencies between agents
  • Time is critical

Example:

Workflow: Comprehensive Security Audit
Coordinator: Multi-Agent Architect

Parallel Execution:
├── Agent 1: OWASP Top 10 checks
├── Agent 2: Dependency vulnerabilities
├── Agent 3: Authentication review
├── Agent 4: Authorization review
└── Agent 5: Data validation review

Aggregation: Combine all findings into report

Read the full file on GitHub · 754 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 · 754 lines · 0 tokens per session scan A 1fdd2850bad5

Subscribe to this mod's changes

agent-workflows is an agent published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,598 tokens. 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.