appendix-coding-agents

appendix-coding-agents is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 441 tokens per session (3,887 once invoked), scanned A, a copy of appendix-coding-agents, MIT.

A guide to using AI agents as coding assistants or as a team of software specialists, while a human developer remains responsible for the final decisions.

In plain words
What is it for?
Use it for software planning, scaffolding, implementation, testing, code review, and conversational prototyping with one or more coding agents.
Why use it?
It gives coding work a clearer structure than treating AI as simple autocomplete, especially when different development tasks need different roles.

Skill for Claude CodeCodex

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 skills/hajekim/agentic-design-patterns-extension/appendix-coding-agents
Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill appendix-coding-agents
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for appendix-coding-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-coding-agents.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-coding-agents)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-coding-agents"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-coding-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 441 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,887 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00441 $0.03887
Opus 5 $0.00220 $0.01944
Sonnet 5 $0.00088 $0.00777
Haiku 4.5 $0.00044 $0.00389

Measured 3d ago against content hash 34a8770a4210, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

appendix-coding-agents 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.

Origin

This is a copy

100% identical to appendix-coding-agents — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/appendix-coding-agents/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Appendix G - Coding Agents

Overview

Coding Agents represent the evolution from simple code completion to a full human-AI augmented development team. The era of the lone coder with an AI autocomplete is giving way to developers who lead teams of specialized AI agents — each with a distinct role in the software development lifecycle.

This appendix presents two complementary paradigms:

  1. Vibe Coding — using conversational LLM interaction for rapid ideation and prototyping
  2. Human-Agent Teams — a structured framework for production software development with specialist agents playing defined roles

As Alphabet CEO Sundar Pichai noted in early 2025: "Over 30% of new code at Google is now assisted or generated by our Gemini models." Microsoft reported similar statistics. The question is no longer whether AI will assist software development, but how to organize that assistance effectively.

Core Principle: The human developer is the architect and final arbiter — agents are force multipliers that handle tactical execution while humans focus on strategic vision and creative problem-solving.

When This Skill Applies

Activate this pattern when:

  • Starting a new feature and want to rapidly prototype before committing to architecture
  • Need comprehensive test coverage for existing code without writing every test manually
  • Generating technical documentation for complex APIs or modules
  • Performing code review with AI-assisted critique and synthesis
  • Building a repeatable, team-wide workflow for AI-assisted development
  • Organizing multiple AI interactions into a coherent, auditable development process

Rule of thumb: Use Vibe Coding to explore. Use the Human-Agent Team framework to build for production.

Vibe Coding: Intuitive AI-Assisted Development

What Is Vibe Coding?

Vibe coding is a conversational approach to software development where you describe the desired outcome (the "vibe") rather than specifying every implementation detail. The AI generates initial code that serves as a creative catalyst for refinement.

Read the full file on GitHub · 347 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 · 347 lines · 441 tokens per session scan A 34a8770a4210

Subscribe to this mod's changes

appendix-coding-agents is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 441 tokens to every session and 3,887 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to appendix-coding-agents, differing in 3 lines, and is treated as a copy.