Ydun_ai_workflow AGENTS.md

A set of instructions and reusable templates for building software with AI assistants.

In plain words
What is it for?
Use it to copy project templates, organize AI-assisted development, and follow initialization and validation checklists.
Why use it?
It gives a project a shared starting point for setup, guidance, status tracking, and development workflow without requiring a framework or build step.

Instructions file for CodexOpenCode

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 instructions/ydun-code-library/ydun_ai_workflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/ydun-code-library/Ydun_ai_workflow

Made for: Codex, OpenCode.

Per session 1,946 This file is loaded in full into every session.
When invoked 1,946 The same file — it is already loaded in full.
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 $0.01946 $0.01946
Opus 5 $0.00973 $0.00973
Sonnet 5 $0.00389 $0.00389
Haiku 4.5 $0.00195 $0.00195

Measured 2d ago against content hash c70b240eb7de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Ydun_ai_workflow AGENTS.md 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.

AGENTS.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ydun AI Workflow — Templates, Prompts, and Patterns for AI-Assisted Development

Version: 3.0.0 Last Updated: 2026-03-09

Repository Information

What This Repo Contains

A collection of production-tested templates, prompt frameworks, and development tools for AI-assisted development. Clone it, copy what you need, fill the placeholders.

This is a distribution repo — pure files, no framework, no build step. The full documentation site with guides, research, and methodology deep-dives is at docs.ydun.io.

Repository Structure

Ydun_ai_workflow/
├── templates/
│   ├── core/                    # Project setup templates
│   │   ├── AGENTS.md.template   # AI assistant guidelines (agents.md standard)
│   │   ├── CLAUDE.md.template   # Claude quick reference
│   │   ├── JIMMYS-WORKFLOW.md   # Validation system v2.1
│   │   ├── STATUS.md.template   # Project status tracking
│   │   └── NEXT-SESSION-START-HERE.md.template
│   ├── init/                    # Project initialisation guides
│   │   ├── init-project.md      # 14-step setup checklist
│   │   └── AGENTS-TEMPLATE-GUIDE.md
│   ├── docs/                    # Documentation standards
│   │   ├── DOCUMENTATION-STANDARDS.md
│   │   ├── AI-DRIVEN-SEO-BEST-PRACTICES.md
│   │   └── doc-components/      # Reusable doc templates
│   └── tools/                   # Shell scripts
│       ├── audit-project.sh     # Compliance audit
│       ├── check-version.sh     # Template version check
│       └── sync-templates.sh    # Template sync utility
├── prompts/
│   ├── audit/                   # Multi-lens audit system
│   │   ├── codebase-audit-prompt.md
│   │   ├── claude-code-audit-prompt.md
│   │   ├── json-sidecar-pattern.md
│   │   └── templates/           # 5 execution templates
│   └── methodology/             # Prompt engineering
│       ├── cap-workflow-methodology.md
│       ├── prompt-testing-implementation-guide.md
│       ├── audit-map-execution-patterns.md
│       └── god-prompt-methodology.md
├── AGENTS.md                    # This file
├── CLAUDE.md                    # Quick reference
├── JIMMYS-WORKFLOW.md           # Workflow v2.1 (full reference)
├── README.md                    # Project overview
├── VERSION                      # Current version
├── llms.txt                     # AI discoverability
└── LICENSE                      # MIT

Read the full file on GitHub · 224 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 · 224 lines · 1,946 tokens per session scan A c70b240eb7de

Subscribe to this mod's changes

Ydun_ai_workflow AGENTS.md is an instructions file published in the GitHub repository ydun-code-library/Ydun_ai_workflow (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,946 tokens to every session, about $0.0097 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 2026-08-31.