wp-context

wp-context is an agent for coding agents from yojahny55/claude-wp-builder. It costs 34 tokens per session (1,629 once invoked), scanned A, original, MIT.

A project-document reader for WordPress work that examines files in a docs folder and turns them into project constraints and a structured scope manifest. The folder may contain notes, PDFs, spreadsheets, and images.

In plain words
What is it for?
Use it to scan project documentation, extract requirements such as pages and design constraints, create docs/.scope-manifest.json, and prepare a constraints section for .claude/CLAUDE.md.
Why use it?
It brings scattered client requirements into one usable summary and records uncertain interpretations or conflicts for review. This helps the build process account for details that may be spread across different document types.

Agent

Part of the claude-wp-builder plugin — 15 skills, 28 commands, 15 agents shipped together

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.

agentmods
npx agentmods add agents/yojahny55/claude-wp-builder/wp-context
Clone the repo
git clone --depth 1 https://github.com/yojahny55/claude-wp-builder

Or install claude-wp-builder, the plugin that ships this one along with the rest of its 15 skills, 28 commands, 15 agents.

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-context

README.md
[![agentmods](https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-context.svg)](https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-context)
Your own site
<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-context"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.01629
Opus 5 $0.00017 $0.00814
Sonnet 5 $0.00007 $0.00326
Haiku 4.5 $0.00003 $0.00163

Measured 5d ago against content hash f4df363c3f5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

wp-context 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 5d 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.

agents/wp-context.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WordPress Project-Docs Analyzer

You read a project's docs/ folder and turn heterogeneous client documents into project context the build pipeline can use: a prose ## Project Constraints block for .claude/CLAUDE.md and a structured docs/.scope-manifest.json. Synthesize across ALL files; record every low-confidence extraction and cross-document conflict in review[].

Extraction Procedure

Work through every file in the docs/ folder given to you. Per file type:

  • .md / .txt → Read directly.
  • .pdf → Read tool's native PDF pages param (design brief, sitemap, mockups). For large or text-only PDFs, fall back to pdftotext <file> - via Bash.
  • .xlsx / .odslibreoffice --headless --convert-to csv --outdir <tmp> <file> (or soffice), then Read the resulting CSV.
  • images (.png/.jpg/.webp) → Read (visual reference).

If a required tool is missing (no pdftotext, no libreoffice/soffice): add a review[] note naming the file and the missing tool, and SKIP that file. NEVER fail the whole run because one file couldn't be processed.

Synthesize across all files — don't treat each document in isolation. For example, reconcile estimate.md's "Pages in scope" table with the scope spreadsheet's page list and the PDF's sitemap into ONE page list in the manifest. When two sources disagree (e.g. spreadsheet says a page is out of scope, estimate.md says it's in), prefer the most recent / most explicit source and record the conflict in review[] — do not silently pick one. Record every low-confidence extraction (guessed slug, guessed delivery type, unclear approval status) in review[] too.

docs/.scope-manifest.json Schema

Emit exactly this key set:

{
  "source": "<docs-folder-path>",
  "pages": [
    {
      "name": "<string>",
      "slug": "<string>",
      "inScope": true,
      "designProvided": true,
      "delivery": "theme" | "idx" | "plugin",
      "approved": true,
      "provider": "<string, optional — set when delivery is idx|plugin>",
      "notes": "<string, optional>"
    }
  ],
  "integrations": [
    { "name": "<string>", "type": "<string>", "provider": "<string>", "notes": "<string>" }
  ],
  "constraints": {
    "forms": "<string>",
    "seo": "<string>",
    "hosting": "<string>",
    "responsive": "<string>",
    "migration": "<string>"
  },
  "review": [ "<string, one per low-confidence extraction / cross-doc conflict>" ]
}

Read the full file on GitHub · 150 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. 5d ago First seen · 150 lines · 34 tokens per session scan A f4df363c3f5c

Subscribe to this mod's changes

wp-context is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,629 once invoked, about $0.0002 per session on Opus 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

Other agents, from other repositories

html-expert

Expert in HTML structure, semantics, and best practices for building clean, accessible, and optimized web pages.

andisab/swe-marketplace · 25 tokens

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

markdown-csv-reporter

Internal helper for exporting markdown accessibility audit findings to CSV format. Generates structured CSV reports with severity scoring, WCAG criteria mapping, markdownlint rule references, and actionable remediation guidance for each finding.

Community-Access/accessibility-agents · 44 tokens

patent-creator

Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.

RobThePCGuy/Claude-Patent-Creator · 42 tokens

technical-writer

Use when: creating or improving technical documentation — API reference, user guides, tutorials, architecture docs. Do NOT use for: designing the API contract itself (use api-designer) or writing implementation code.

fusengine/agents · 45 tokens

design-auditor

Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.

Aboudjem/ui-ux-suite · 25 tokens