WordPress
Open source CMS that runs a huge chunk of the web, plus a paid hosted tier and an infinite plugin economy.
The thing people actually use WordPress for on a personal site, write posts, upload images, publish, have an RSS feed, is a weekend build and always has been. An agent can hand you a SQLite-backed CMS with a markdown editor, media uploads, drafts, tags, and a sitemap in one sitting, and it will be faster and less hackable than the real thing. What you cannot one-shot is the other 90 percent of WordPress: 60,000 plugins, WooCommerce, Yoast, Elementor, the block editor, and the fact that any freelancer on earth can pick up your site. Also worth noting that core WordPress is already free and self-hostable, so the honest question is whether you want to maintain your own CMS instead of someone else's. If your site has a contact form, a store, or a client who needs to log in, stop reading and just install WordPress.
Build verification: not recorded. How we judge buildability
What you give up
- The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build
- WooCommerce and anything resembling commerce
- Gutenberg block editing and the visual page builders non-technical people actually like
- A theme marketplace, so your site looks like whatever the agent felt like that day
- Any hope of handing the site to a developer who already knows the stack
- Security updates and managed hosting done by someone who is not you
Why people still pay
Almost nobody pays for WordPress the software. They pay for managed hosting so the site stays up and patched, for the three or four plugins that quietly run their business, and for the person who knows how to fix it when the theme update explodes. A personal CMS you built yourself removes the hosting bill and adds an on-call rotation of one. That trade is fine for a blog and terrible for anything that takes money.
Your build guide
The stack, security requirements, and agent rules for a focused replacement.
Before you start
- Node, persistent local database/uploads, public HTTPS hosting and a generated administrator password hash kept outside source. No WordPress runtime or plugin compatibility is implied.
- Implementation components: Node.js, TypeScript and Fastify with Eta server-rendered HTML. SQLite via better-sqlite3, sanitized markdown-it rendering, Sharp media processing and authenticated administrator cookie sessions.
- Scope boundary: The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce
Use these project rules and optional skill references alongside the prompt. Review each skill before adding it to your agent; the AGENTS.md export includes the same guidance.
Optional external skill: web-design-guidelines — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: sharp-edges — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: posts, unique slugs, draft/published revisions, media assets, tags and RSS publication state
Project rule — preserve this invariant: Markdown and uploads cannot execute scripts; publishing is an explicit action and deleted/draft posts cannot leak through feeds or search.
Project rule — acceptance evidence: Save a draft and confirm it is absent from RSS and public routes; change a published slug with a deliberate redirect and preserve the original revision.
Implementation plan
Phase 1
Scope and fixtures. Implement this bounded workflow: Build a single-author Markdown CMS with one authenticated administrator, image uploads and server-rendered public pages. Include preview, RSS, redirects for deliberate slug changes and a complete source export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce
Phase 2
Durable model. Model posts, unique slugs, draft/published revisions, media assets, tags and RSS publication state Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Markdown and uploads cannot execute scripts; publishing is an explicit action and deleted/draft posts cannot leak through feeds or search.
Phase 3
Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
Phase 4
Permissions and integration failure. Public routes accept only their documented inputs with rate/size limits. Protect every owner/customer action with authenticated authorization and CSRF checks; keep secrets outside exports and redact personal data from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
Phase 5
Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
Phase 6
Acceptance scenarios. Save a draft and confirm it is absent from RSS and public routes; change a published slug with a deliberate redirect and preserve the original revision. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.
WORKING SLICE Build a single-author Markdown CMS with one authenticated administrator, image uploads and server-rendered public pages. Include preview, RSS, redirects for deliberate slug changes and a complete source export. Build this scoped WordPress-inspired workflow with a documented data model and visible failure states. Architecture - Node.js, TypeScript and Fastify with Eta server-rendered HTML. - SQLite via better-sqlite3, sanitized markdown-it rendering, Sharp media processing and authenticated administrator cookie sessions. Prerequisites and limits Node, persistent local database/uploads, public HTTPS hosting and a generated administrator password hash kept outside source. No WordPress runtime or plugin compatibility is implied. Outside this release: The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce Data model and correctness posts, unique slugs, draft/published revisions, media assets, tags and RSS publication state Invariant: Markdown and uploads cannot execute scripts; publishing is an explicit action and deleted/draft posts cannot leak through feeds or search. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. Security and privacy Public routes accept only their documented inputs with rate/size limits. Protect every owner/customer action with authenticated authorization and CSRF checks; keep secrets outside exports and redact personal data from logs. Recovery and export Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Implementation order 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Build a single-author Markdown CMS with one authenticated administrator, image uploads and server-rendered public pages. Include preview, RSS, redirects for deliberate slug changes and a complete source export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce 2. Phase 2 — Durable model. Model posts, unique slugs, draft/published revisions, media assets, tags and RSS publication state Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Markdown and uploads cannot execute scripts; publishing is an explicit action and deleted/draft posts cannot leak through feeds or search. 3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. 4. Phase 4 — Permissions and integration failure. Public routes accept only their documented inputs with rate/size limits. Protect every owner/customer action with authenticated authorization and CSRF checks; keep secrets outside exports and redact personal data from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. Save a draft and confirm it is absent from RSS and public routes; change a published slug with a deliberate redirect and preserve the original revision. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance Save a draft and confirm it is absent from RSS and public routes; change a published slug with a deliberate redirect and preserve the original revision. Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees. Optional agent guidance Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Project rule — data model: posts, unique slugs, draft/published revisions, media assets, tags and RSS publication state Project rule — preserve this invariant: Markdown and uploads cannot execute scripts; publishing is an explicit action and deleted/draft posts cannot leak through feeds or search. Project rule — acceptance evidence: Save a draft and confirm it is absent from RSS and public routes; change a published slug with a deliberate redirect and preserve the original revision.
$ open in your agent (prompt prefilled, you press enter), copy the prompt or copy or download AGENTS.md · generated from this app's build plan
prompt copied. want to know what dies next week?
new verdicts + top votes, weekly. free. one-click out.
No prior-art project is listed yet. Compare the scoped build with the paid product before choosing.
Questions about WordPress
Can you build your own WordPress with AI?
Partly. The thing people actually use WordPress for on a personal site, write posts, upload images, publish, have an RSS feed, is a weekend build and always has been. An agent can hand you a SQLite-backed CMS with a markdown editor, media uploads, drafts, tags, and a sitemap in one sitting, and it will be faster and less hackable than the real thing. What you cannot one-shot is the other 90 percent of WordPress: 60,000 plugins, WooCommerce, Yoast, Elementor, the block editor, and the fact that any freelancer on earth can pick up your site. Also worth noting that core WordPress is already free and self-hostable, so the honest question is whether you want to maintain your own CMS instead of someone else's. If your site has a contact form, a store, or a client who needs to log in, stop reading and just install WordPress.
What does the WordPress build prompt cover?
The prompt starts with this scope: Build a single-author Markdown CMS with one authenticated administrator, image uploads and server-rendered public pages. Include preview, RSS, redirects for deliberate slug changes and a complete source export. Full-product capabilities excluded from the comparison include: The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce; Gutenberg block editing and the visual page builders non-technical people actually like. Follow the implementation plan and its prerequisites before expanding the build.
How do I use the prompt, AGENTS.md and agent skills?
Start with the WordPress prerequisites and stack, then copy the prompt into your coding agent. Save the project rules as AGENTS.md in the project root. Linked skills are optional packages or source instructions for specific tasks; review their current contents and install only those matching the chosen stack. A skill does not supply API credentials or verify the finished app.
How long will this WordPress project take?
The catalogue estimate is a weekend for the limited scope. Setup, integration approvals, debugging, deployment and ongoing maintenance can add time. This is an estimate, not a delivery guarantee.
What would I give up by replacing WordPress?
The plugin ecosystem: SEO, forms, caching, memberships, analytics, backups, all one click away in WordPress and all your problem in the DIY build; WooCommerce and anything resembling commerce; Gutenberg block editing and the visual page builders non-technical people actually like; A theme marketplace, so your site looks like whatever the agent felt like that day; Any hope of handing the site to a developer who already knows the stack; Security updates and managed hosting done by someone who is not you. Almost nobody pays for WordPress the software. They pay for managed hosting so the site stays up and patched, for the three or four plugins that quietly run their business, and for the person who knows how to fix it when the theme update explodes. A personal CMS you built yourself removes the hosting bill and adds an on-call rotation of one. That trade is fine for a blog and terrible for anything that takes money.
What price is this guide comparing against?
The recorded Personal plan is $4/mo (per month, billed annually), checked 2026-08-18. Check the linked pricing source before buying. Building your own also has hosting, API and maintenance costs; the recorded amount is not a guaranteed saving.
What can I use instead of building WordPress?
No alternative is listed in this entry yet. That is a gap in this catalogue, not proof that no suitable product exists. Compare the paid product and the proposed scope before committing to a build.