wp-agentic-surfaces

wp-agentic-surfaces is an agent for Claude Code from yojahny55/claude-wp-builder. It costs 60 tokens per session (13,004 once invoked), scanned A, original, MIT.

A WordPress theme agent that adds files and settings intended to make a site easier for AI agents and generative search systems to read. It works with items such as llms.txt, agent-skill indexes, machine-readable page data, links, and the robots policy.

In plain words
What is it for?
Use it to apply the fixable findings from a WordPress GEO audit, add agent-facing site surfaces, and write the site's AI crawler policy through WP-CLI.
Why use it?
It addresses missing or unclear machine-readable information that can make a WordPress site harder for automated readers to discover and understand.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; positional $N argument.

Part of the claude-wp-builder plugin — 35 skills, 36 commands, 19 agents, 1 MCP server shipped together

Good fit Use it to apply the fixable findings from a WordPress GEO audit, add agent-facing site surfaces, and write the site's AI crawler policy through WP-CLI.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yojahny55/claude-wp-builder/wp-agentic-surfaces
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.

Clone the repo
git clone --depth 1 https://github.com/yojahny55/claude-wp-builder

Made for: Claude Code.

Or install claude-wp-builder, the plugin that ships this one along with the rest of its 35 skills, 36 commands, 19 agents, 1 MCP server.

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 wp-agentic-surfaces

README.md
[![agentmods](https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces/github.svg)](https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces)
Your own site
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces/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 wp-agentic-surfaces

Your own site · 80×15
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-agentic-surfaces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 13,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00060 $0.13004
Opus 5.5 $0.00024 $0.05202
Sonnet 5.5 $0.00012 $0.02601
Haiku 4.5 $0.00006 $0.01300

Measured 6d ago against content hash 31cfe7eb4152, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wp-agentic-surfaces scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return (bool) preg_match( '/bot|crawl|spider|agent|curl|wget|python|httpx|libwww|httpclient/i', $ua );
agents/wp-agentic-surfaces.md · 1,016 lines

How it starts

The opening of the file, as written. The whole thing — 1,016 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Surfaces Fixer

You make a WordPress site readable by AI agents and generative engines by writing one theme-owned file, inc/agentic.php, requiring it from functions.php, seeding the trust anchors and writing the robots AI policy. Reference the wp-audit-geo-standards skill for every surface's spec, the crawler allowlist and the applicability matrix. You consume the site type and the fixable findings from wp-audit-geo. All WordPress interaction via WP-CLI.

First Action (MANDATORY)

Before writing any file or running any command, read the project files:

  1. .claude/CLAUDE.md — Extract:

    • The function prefix (recorded with a trailing underscore, e.g., kairo_). Use its bare form without the trailing underscore for every <prefix> in the templates below, so <prefix>_llms_txt becomes kairo_llms_txt and <prefix>_get_field becomes kairo_get_field, matching the project helper recorded in .claude/CLAUDE.md. If in doubt, read an existing theme function name and copy its exact prefix.
    • The theme slug and theme path (where functions.php and inc/ live)
    • The industry (a local/business value is one positive signal for the local site type)
    • The languages configured
  2. .wp-create.json — Extract:

    • The WP-CLI wrapper command (wp_cli.wrapper) — assign to $WP
  3. skills/wp-audit-geo-standards/SKILL.md — the surface specs, the AI crawler allowlist and the applicability matrix.

Determine the site type from positive, recorded signals — never by scanning REST namespaces. Check in order:

  • class_exists( 'WooCommerce' ) (via $WP plugin is-active woocommerce, the test /wp-audit Step 2.3 records as site.commerce) → merchant
  • the project's Industry is a local/business value and the settings carry a non-empty business_address → local
  • the audit or .claude/CLAUDE.md records a SaaS / public-API site (an OpenAPI spec or a deliberate public API surface) → saas
  • otherwise → content

Read the full file on GitHub · 1,016 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. 6d ago Changed 31cfe7eb4152
  2. 7d ago Changed · +15 lines f3b5ae83cced
  3. 10d ago Changed · +9 lines e9bb2198d57b
  4. 11d ago Changed 9e74f8fc6da2
  5. 14d ago Changed d8b2f694b1c9
  6. 29d ago Changed · +44 lines 871fa60989a4
  7. 1mo ago First seen · 948 lines · 60 tokens per session scan A 60d7545e1dc5

Subscribe to this mod's changes

wp-agentic-surfaces is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 13,004 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.