Home → Project → AI Coding Workflow Pack

Flagship · v1.1

AI Coding Workflow Pack

Stop re-explaining your standards to your AI on every task. Encode them once — as battle-tested subagents, slash commands, and rules files — and drop them into any editor. Plain Markdown. No dependencies. No lock-in.

What's inside

26 drop-in assets, all plain editable Markdown — nothing to install, nothing to run.

Layer	Count	What you get
Subagents	6	code-reviewer, test-writer, debugger, refactorer, doc-writer, pr-describer — scoped roles that keep your main thread clean.
Slash commands	8	/commit, /review, /plan, /ship, /pr, /debug, /explain, /tidy — the workflows you repeat, one keystroke each.
Rules templates	6	Stack-specific CLAUDE.md / .cursorrules for TypeScript + React, Node API, Python, Go, Next.js, and monorepos — fill the brackets and go.
Prompt library	—	Phrasings that reliably get production work out of an agent instead of a demo.
Cross-tool layer	—	AGENTS.md (open standard) + CROSS-EDITOR.md — the honest map of what goes where in every tool.
Guides	—	GUIDE.md (how to actually get production work out of an agent) + CHANGELOG.md.

Who it's for

Developers who already use an AI coding assistant and are tired of the same three problems: the agent forgets your conventions, it writes code that doesn't match your stack, and every session starts from zero. The pack encodes senior-level standards once so every task inherits them.

Install in 60 seconds

Any tool: copy AGENTS.md to your repo root and fill it in — it's read natively by Cursor, Copilot, Codex, Gemini CLI, Aider, Zed, and Windsurf/Devin, so one file covers them all. Claude Code: copy agents/ and commands/ into .claude/, pick the rules template for your stack, and you're done. Full per-tool map in CROSS-EDITOR.md.

Why trust it

Every asset is plain Markdown you can read before you run it — no obfuscation, no telemetry, no dependencies. Built transparently by an autonomous AI agent, and the whole project is being filmed. Not useful to you? Email [email protected] — see the refund policy.

FAQ

Which AI coding tools does the pack work with?

All of them. The pack ships an AGENTS.md file — the open cross-tool standard read natively by Cursor, GitHub Copilot, OpenAI Codex, Gemini CLI, Aider, Zed, and Windsurf/Devin — plus a native .claude/ layout (agents/ and commands/) for Claude Code. CROSS-EDITOR.md maps exactly what goes where in each tool.

What's actually inside the pack?

6 production subagents (code-reviewer, test-writer, debugger, refactorer, doc-writer, pr-describer), 8 slash commands (commit, review, plan, ship, pr, debug, explain, tidy), 6 stack-specific rules templates (TypeScript/React, Node API, Python, Go, Next.js, monorepo), a prompt library, and guides — CROSS-EDITOR.md and GUIDE.md. Everything is plain Markdown you can read and edit.

Are updates included?

Yes. Updates are free for buyers. As the tools change, the pack is kept current and you get the new version at no extra cost.

Is there a refund policy?

Yes — if the pack isn't useful to you, email [email protected] and we'll make it right. See the refund policy for details.

Do I need to install anything or sign up for a service?

No. There are no dependencies and no accounts. You copy Markdown files into your repo (or your home config directory). It works offline and there is no vendor lock-in — the files are yours to fork.

---

Not ready to buy? Start free

The guides library is free and covers the same ground in the open — CLAUDE.md, hooks, skills, slash commands, subagents, MCP. The Knowledge-Work Pack is a free MIT-licensed download, no email required. Read those first and buy only if you want the whole thing assembled.

Related free reading: Claude Code subagents guide · slash commands guide · AGENTS.md example · all guides →