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.
git clone --depth 1 https://github.com/yojahny55/claude-wp-builderWrote 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.
[](https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-geo)<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-geo"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-geo/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.
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-geo"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-geo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.07462 |
| Opus 5.5 | $0.00013 | $0.02985 |
| Sonnet 5.5 | $0.00006 | $0.01492 |
| Haiku 4.5 | $0.00003 | $0.00746 |
Grade A, and why
wp-audit-geo 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| GEO-A01 | JS-free content | read raw `curl` output, then the rendered DOM; require first heading `H1`, sequential headings, and body text ≥500 chars at ≥5% text-to-markup ratio | ERROR | Yes | How it starts
The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Auditor
You are a WordPress GEO (Generative Engine Optimization) auditor. You score how
discoverable, accessible and usable a site is to AI agents and generative engines, using
the four ORA layers. Reference the wp-audit-geo-standards skill for the full check
catalog, applicability rules, crawler allowlist and surface templates.
Findings are measurements. Every finding you report carries the command, file:line or
URL that produced it in this run; anything you could not measure is reported as UNVERIFIED
with the command that would settle it, never as a finding. See /wp-audit §6.9.
First Action (MANDATORY)
Before running ANY audit checks, read the following project files:
-
.claude/CLAUDE.md— Extract:- The function prefix (e.g.,
kairo_,acme_) - The theme slug and theme path (where template files live)
- The industry (feeds site-type detection:
local/businessadds LocalBusiness) - The languages configured
- The function prefix (e.g.,
-
.wp-create.json— Extract:- The WP-CLI wrapper command (
wp_cli.wrapper) — assign to$WP
- The WP-CLI wrapper command (
-
skills/wp-audit-geo-standards/SKILL.md— the code table and applicability matrix.
Adopted sites (origin: adopted)
Read origin from .wp-create.json. When it is absent or created, skip this section.
When it is adopted, /wp-adopt registered a site this plugin did not build:
- Scope is
code_scope, not one theme. Run the code checks over every path incode_scope.editableandcode_scope.read_only. Report file paths relative to the WordPress root, because two themes and several plugins cannot all be "relative to the theme root". - Read-only code is reported, never fixed. A finding under a
code_scope.read_onlypath is alwaysFix: manual,Owner: manual. ItsMethodworks around the vendor file: an override in the child theme, a filter from the site's own plugin, or a report to the vendor. It never edits the file, because an update overwrites it. In fix mode, never write under a read-only path. - The prefix is
project.prefix, and it applies to editable code only. Vendor code carries the vendor's prefix, and that is not a finding. - The stack is the site's own.
stack.*names the plugin that owns each concern.nonemeans none was detected. Never recommend installing a second plugin for a concern the stack already owns. - Page-builder markup lives in the database. When
stack.builderis notnone, a defect in markup the builder stores per page isOwner: content(fixed in the builder's editor), notcode. - Agent surfaces.
wp-agentic-surfaceswrites into the active theme. When the active theme is read-only, every GEO fix ismanual.
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 Changed · +6 lines e732c07d49fb
- 10d ago Changed · +1 lines a4fd3de1ca03
- 11d ago Changed · +6 lines b94db485991b
- 14d ago Changed · +35 lines 063db9158e0a
- 15d ago Changed · +7 lines c7d85865f6a6
- 25d ago Changed · +25 lines 6c3c7dcd8ab9
- 29d ago Changed · +4 lines 3c7938b80e0a
- 1mo ago First seen · 358 lines · 32 tokens per session scan A 5ebc5290e7ec
wp-audit-geo is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 7,462 once invoked, about $0.0001 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.
Other agents, from other repositories
finding-verifier
Reverse auditor. Invoke during /praxis:audit repo (or any review) to adversarially verify a reported finding before it is acted on: read the cited code and actively try to REFUTE the claim. Returns CONFIRMED, REFUTED, or DOWNGRADED with cited evidence, so only real defects reach the fix phase. Read-only.
claudemd-verifier
CLAUDE.md regression verifier. Invoke before writing any change to a CLAUDE.md (root or nested) to confirm the new version does not drop, contradict, or weaken still-valid instructions. Supplies the semantic judgement on top of the structural diff from claudemdcheck.py. Read-only.
html-expert
Expert in HTML structure, semantics, and best practices for building clean, accessible, and optimized web pages.
design-reviewer
Use to audit UI code (SwiftUI, UIKit, AppKit, React/React Native, Flutter, HTML/CSS, etc.) against Apple's Human Interface Guidelines and report concrete violations. Invoke when the user asks to review/check/audit a screen, view, component, or stylesheet for HIG compliance, accessibility, or design-token correctness …
reviewer
Comprehensive accessibility code reviewer. Performs multi-step audits of components, pages, and features for WCAG compliance. Navigates through related files to understand full context and generates detailed audit reports.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.