arwp-site-focus

arwp-site-focus is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 61 tokens per session (3,446 once invoked), scanned A, original, Apache-2.0.

A planning method for defining a website's audience, problem area, scope, page structure, navigation, visual system, and performance limits before expanding it. It is intended for new site builds and redesigns.

In plain words
What is it for?
Use it to set what the site includes and excludes, define its homepage and navigation, assign user problems to site sections, and record experience budgets.
Why use it?
It prevents a website from becoming broad, fragmented, or driven by features before its purpose is clear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node bin/arwp-focus.mjs https://example.com --focus-profile=.arwp/site-focus.json.

Good fit Use it to set what the site includes and excludes, define its homepage and navigation, assign user problems to site sections, and record experience budgets.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profile
agentmods
npx agentmods add skills/dkharlanau/agent-ready-web-profile/arwp-site-focus

Made for: Claude Code, Codex.

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 arwp-site-focus

README.md
[![agentmods](https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus/github.svg)](https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus)
Your own site
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus/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 arwp-site-focus

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-site-focus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00061 $0.03446
Opus 5 $0.00030 $0.01723
Sonnet 5 $0.00012 $0.00689
Haiku 4.5 $0.00006 $0.00345

Measured yesterday against content hash 246ed7506ce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arwp-site-focus 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 yesterday.

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.

skills/arwp-site-focus/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP site focus

Use this skill before arwp-discoverability, arwp-ai-search-content, broad content expansion or a visual redesign. A site should first be coherent enough that a person can explain what problem territory it owns, for whom, which first-order problem lanes it exposes and what it intentionally leaves out.

This is a product/design gate, not a claimed search ranking factor. Numeric limits are Goose house heuristics or owner-declared budgets unless an upstream source explicitly defines them. Never turn them into a composite readiness/focus/beauty score.

Workflow

Prefer Site Focus v0.3 whenever the owner/repository context is available. v0.2 remains backward compatible.

  1. Declare intended product truth in .arwp/site-focus.json: thesis, IN / ADJACENT / OUT scope, problem lanes, homepage contract, primary navigation, route roles and experience budgets.
  2. Give every problem lane an audience, concrete problem, desired outcome and primary action. A lane is a user job, not a technology bucket.
  3. Declare which lane owns the homepage and which signals it must communicate: problem, audience, outcome, evidence and action.
  4. Observe the generated/public site with arwp-focus.
  5. Compare declared intent with observed implementation: homepage-lane drift, required-signal drift, lane-to-route coverage, navigation budget, page contracts, locale-equivalence and unclassified routes.
  6. Keep visual principles as owner intent and Core Web Vitals as field-evidence budgets. Static HTML inspection must not fabricate visual quality or performance evidence.
  7. Pass only accepted decisions forward. Focus may emit proposal-only Target Transformation handoff candidates, but it never authorizes mutations itself.

Run the executable report when a public site or generated repository surface exists:

node bin/arwp-focus.mjs https://example.com --focus-profile=.arwp/site-focus.json
node bin/arwp-focus.mjs https://example.com --focus-profile=.arwp/site-focus.json --max-pages=30 --json
node bin/arwp-focus.mjs https://example.com/project/ --repo-root=. --output=site-focus-report.json

Read the full file on GitHub · 290 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. yesterday Changed 246ed7506ce6
  2. 2d ago First seen · 290 lines · 61 tokens per session scan A 9c6d3ed7b93f

Subscribe to this mod's changes

arwp-site-focus is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 3,446 once invoked, about $0.0003 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 2026-09-09.