agent-workflows

A guide to connecting specialized coding agents into ordered workflows. A workflow is a sequence in which different agents plan, build, test, review, deploy, or document work.

In plain words
What is it for?
Use it to organize feature development, bug fixes, refactoring, API work, project setup, continuous integration and deployment, security checks, and documentation.
Why use it?
It helps choose which agent should handle each stage and when work should pass from one agent to another.

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/dhar174/custom_github_copilot_agent_builder/agent-workflows
Clone the repo
git clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builder
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 7,461 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 $0.07461
Opus 5 $0.00000 $0.03730
Sonnet 5 $0.00000 $0.01492
Haiku 4.5 $0.00000 $0.00746

Measured 2d ago against content hash 49450bc28001, 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 2d 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.

.github/agents/agent-workflows.md · 762 lines

How it starts

The opening of the file, as written. The whole thing — 762 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This document visualizes the relationships between custom agents and defines logical workflow sequences for common development tasks.

Agent Ecosystem Overview

graph TB
    subgraph "Planning & Design"
        plan[Plan Mode]
        architect[Architect]
        prd[PRD Creator]
        spec[Specification]
        implplan[Implementation Plan]
    end
    
    subgraph "Implementation"
        pse[Principal Software Engineer]
        clean[Clean Code Agent]
        debug[Debug Agent]
    end
    
    subgraph "Quality Assurance"
        test[Test Writer]
        security[Security Reviewer]
        review[Code Reviewer]
    end
    
    subgraph "DevOps & Deployment"
        devops[DevOps Expert]
        ghactions[GitHub Actions Expert]
    end
    
    subgraph "Documentation"
        refine[Refine Issue]
        tech-content[Technical Content]
    end
    
    subgraph "Meta & Support"
        foundry[Custom Agent Foundry]
        mentor[Mentor]
        research[Research & Spike]
    end

    classDef planning fill:#e1f5ff,stroke:#01579b,stroke-width:2px
    classDef implementation fill:#f3e5f5,stroke:#4a148c,stroke-width:2px
    classDef quality fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef devops fill:#e8f5e9,stroke:#1b5e20,stroke-width:2px
    classDef docs fill:#fce4ec,stroke:#880e4f,stroke-width:2px
    classDef meta fill:#f1f8e9,stroke:#33691e,stroke-width:2px
    
    class plan,architect,prd,spec,implplan planning
    class pse,clean,debug implementation
    class test,security,review quality
    class devops,ghactions devops
    class refine,tech-content docs
    class foundry,mentor,research meta

Workflow 1: Feature Development (Complete Cycle)

Requirements

  • REQ-001: All features must begin with planning and requirements documentation before implementation
  • REQ-002: Technical specifications must be created from approved PRDs before architectural design
  • REQ-003: Architecture decisions must be documented and reviewed before implementation planning
  • REQ-004: Implementation must include automated tests with minimum 80% code coverage
  • REQ-005: Security review must be performed before deployment
  • REQ-006: DevOps deployment strategy must be defined and tested

Read the full file on GitHub · 762 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. 2d ago First seen · 762 lines · 0 tokens per session scan A 49450bc28001

Subscribe to this mod's changes

agent-workflows is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,461 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 2026-08-31.