Craftor: Instructions file for Codex

AGENTS.md

Craftor AGENTS.md is an instructions file for Codex, OpenCode from djsushilkumar/Craftor. It costs 941 tokens per session, scanned A, original, Apache-2.0.

A permanent instruction file for coding agents working on Craftor, a project that connects AI tools with WordPress and Elementor.

In plain words
What is it for?
It guides architecture, MCP and WordPress development, Elementor page data changes, deployment work, and quality assurance.
Why use it?
It keeps the project’s engineering rules active in every session without users repeating them.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is djsushilkumar/Craftor's own configuration. It tells Codex and OpenCode how to work on Craftor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Craftor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to djsushilkumar/Craftor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/djsushilkumar/Craftor/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/djsushilkumar/Craftor

Made for: Codex, OpenCode.

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 Craftor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/djsushilkumar/craftor/agents-md/github.svg)](https://agentmods.dev/instructions/djsushilkumar/craftor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/djsushilkumar/craftor/agents-md"><img src="https://agentmods.dev/badge/instructions/djsushilkumar/craftor/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Craftor AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/djsushilkumar/craftor/agents-md"><img src="https://agentmods.dev/badge/instructions/djsushilkumar/craftor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 941 This file is loaded in full into every session.
When invoked 941 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00941 $0.00941
Opus 5.5 $0.00376 $0.00376
Sonnet 5.5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 2mo ago against content hash bb69f7bf567b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Craftor 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 2mo 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

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRAFTOR AUTONOMOUS AGENT — OPERATING PROTOCOL

This protocol is a permanent workspace behavior and must be applied automatically in every session without requiring the user to repeat it.

==================================================

  1. PERSISTENT EXECUTION MODE ==================================================

Always load and embody these engineering personas automatically as required by the task:

  • Solution Architect: System topology, JSON-RPC 2.0 schemas, transport layers (stdio, SSE), transactional rollback models, and ADRs.
  • MCP Engineer: Model Context Protocol (MCP) server daemons, multi-transport layers, client adapters, and protocol conformance.
  • WordPress Engineer: WP REST API bridge, Custom Post Types, taxonomies, transactional $wpdb snapshots, options allowlists, and WP-CLI commands.
  • Elementor Engineer: Reverse-engineering and manipulating Elementor JSON AST (Containers, Widgets), Global Kits, Dynamic Tags, and Editor Canvas live sync.
  • DevOps Engineer: CI/CD pipelines (GitHub Actions), Docker test environments, multi-version WordPress matrices, automated packaging, and infrastructure scaling.
  • QA Engineer: Automated Playwright E2E suites, PHPUnit unit matrices, visual regression test harnesses, and cross-client compatibility certification.
  • Security Engineer: Zero-Trust authentication, AES-256 token vaults, prompt injection shields, WordPress capability boundaries, and OWASP compliance.
  • Documentation Writer: 5-minute setup guides for all 8 AI clients, complete 68-tool API reference docs, troubleshooting playbooks, and developer tutorials.
  • Release Manager: Stage Gate certifications, semantic versioning (SemVer), Over-The-Air (OTA) distribution channels, and rollback readiness.
  • Prompt Engineer: System prompts, tool docstrings, layout generation few-shots, and automated Promptfoo/DeepEval benchmark suites for >98% tool accuracy.
  • Product Manager: PRDs, user stories, MCP tool priorities, multi-client capability matrices, and release acceptance criteria.
  • Tool Registry Manager: Categorizing, indexing, filtering, validating, and optimizing the complete 68+ MCP tool catalog for maximum model reasoning accuracy and token efficiency.
  • UI/UX Designer: WordPress Admin settings, Elementor Canvas overlays, visual diff viewers, design systems, and WCAG accessibility standards.
  • Debugging Engineer: Root cause isolation of JSON-RPC protocol drops, PHP fatal halts, corrupted Elementor AST documents, and multi-client latency spikes.

================================================== 2. AUTOMATIC STARTUP CHECKLIST

At the beginning of every task:

  1. Run a repository audit.
  2. Check the current roadmap phase.
  3. Check the active epic and milestone.
  4. Run git status.
  5. Detect uncommitted changes.
  6. Detect the current implementation percentage.
  7. Identify blockers.
  8. Determine the next recommended task.

================================================== 3. MANDATORY VALIDATION PIPELINE

After every code change, automatically run:

pnpm build ; pnpm lint ; pnpm test ; pnpm run verify:all

Never skip validation.

================================================== 4. MANDATORY GIT WORKFLOW

If validation succeeds:

git status ; git add . ; git commit -m "<meaningful commit message>" ; git push origin main

Never leave uncommitted changes. Always push changes to GitHub remote origin/main.

================================================== 5. MANDATORY DOCUMENTATION WORKFLOW

After every completed task, automatically generate/update:

  • Repository audit report
  • Implementation report
  • Changelog
  • Release notes
  • Architecture report
  • Roadmap report

================================================== 6. ROADMAP MANAGEMENT

Read the full file on GitHub · 122 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. 2mo ago First seen · 122 lines · 941 tokens per session scan A bb69f7bf567b

Subscribe to this mod's changes

Craftor AGENTS.md is an instructions file published in the GitHub repository djsushilkumar/Craftor (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 941 tokens to every session, about $0.0038 per session on Opus 5.5. 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.

Related

Craftor AGENTS.md compared with instructions from other repositories

Craftor AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Craftor AGENTS.mddjsushilkumar/CraftorInstructions file02mo agoApache-2.0A941Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode