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.
npx agentmods add instructions/hypercart-dev-tools/ai-ddtk-fix-iterate-loop/agents-mdgit clone --depth 1 https://github.com/Hypercart-Dev-Tools/AI-DDTK-Fix-Iterate-LoopWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.06099 | $0.06099 |
| Opus 5 | $0.03050 | $0.03050 |
| Sonnet 5 | $0.01220 | $0.01220 |
| Haiku 4.5 | $0.00610 | $0.00610 |
Grade A, and why
AI-DDTK-Fix-Iterate-Loop 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 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.
How it starts
The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress Development and Architecture Guidelines for AI Agents
Last updated: 2026-03-25 · Toolkit version: see CHANGELOG.md
Purpose
Defines principles, constraints, and best practices for AI agents and Humans working with WordPress code to ensure safe, consistent, and maintainable contributions.
README.md is the high-level hub; this file is the canonical source of truth for agent workflow, tool usage, and WordPress-specific guidance.
🚀 Getting Started
This workspace uses AI-DDTK (AI Driven Development ToolKit) installed at ~/bin/ai-ddtk.
Session Preflight Check (Recommended First Step)
Before starting any WordPress task, run a preflight check to verify the toolkit is ready.
There are two modes — use whichever fits your context:
| Mode | When to use | Command |
|---|---|---|
| Shell preflight | Quick human/CI check, no MCP needed | ./preflight.sh |
| MCP-aware preflight | Agent sessions with MCP tools available | Follow the prompt in experimental/preflight.md |
Shell preflight (./preflight.sh) can also be run from the VS Code task palette:
- Press
Cmd+Shift+P(macOS) orCtrl+Shift+P(Linux/Windows) - Search for "AI-DDTK: Preflight Check"
- Press Enter
What preflight verifies:
- AI-DDTK installation at
~/bin/ai-ddtk - Shell tools (rg, php, node, python3, git, tmux)
- WPCC availability and features
- MCP server build status and editor configuration
- WordPress site context (Local WP or WP-CLI)
The MCP-aware preflight additionally probes live MCP tool connectivity, WordPress site info, and Playwright auth status.
Why? AI agents often forget about third-party tools and don't verify toolkit readiness before starting work. Preflight ensures everything is ready in seconds and suggests exact fix commands if anything is missing.
If preflight detects missing items:
- Run the suggested command (e.g.,
~/bin/ai-ddtk/install.sh setup-mcp) - Re-run preflight to confirm:
./preflight.sh - Proceed with your task
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.
- 3d ago First seen · 520 lines · 6,099 tokens per session scan A 03276a66f0c3
AI-DDTK-Fix-Iterate-Loop AGENTS.md is an instructions file published in the GitHub repository Hypercart-Dev-Tools/AI-DDTK-Fix-Iterate-Loop (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 6,099 tokens to every session, about $0.0305 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.