arwp-ai-search-content

arwp-ai-search-content is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 86 tokens per session (1,279 once invoked), scanned A, original, Apache-2.0.

A set of instructions for improving website content so people, search engines, and AI search tools can find, understand, compare, and cite it. AI search tools answer questions by retrieving information from online pages.

In plain words
What is it for?
Use it to improve articles, documentation, landing pages, comparisons, answer pages, and other knowledge content for search and AI citations.
Why use it?
It helps prevent vague, repetitive content and makes the page's real answer, evidence, and purpose easier to retrieve.

Skill for Claude CodeCodex

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

Good fit Use it to improve articles, documentation, landing pages, comparisons, answer pages, and other knowledge content for search and AI citations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dkharlanau/agent-ready-web-profile/arwp-ai-search-content
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.

Any agent
npx skills add dkharlanau/agent-ready-web-profile --skill arwp-ai-search-content
Clone the repo
git clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profile

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-ai-search-content

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-ai-search-content"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-ai-search-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 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 $0.00086 $0.01279
Opus 5 $0.00043 $0.00639
Sonnet 5 $0.00017 $0.00256
Haiku 4.5 $0.00009 $0.00128

Measured 3d ago against content hash 980985901df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

arwp-ai-search-content 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 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.

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-ai-search-content/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP AI Search Content

Use this skill to improve content quality for humans first, while making the content easier for search and AI systems to retrieve, understand, cite, compare and route.

Core rule

Do not rewrite content into generic "AI SEO" prose. Google explicitly emphasizes useful, original, non-commodity content rather than special AI-only markup. Treat special AI files as supporting surfaces, not ranking shortcuts.

Before editing, use docs/ANTI-PATTERNS.md and knowledge/research/anti-patterns.json to review applicable negative examples. Record context and false-positive boundaries using templates/growth/anti-pattern-review.md; automated text matches cannot prove low quality.

Workflow

  1. Identify the page's real job.

    • What user problem does it solve?
    • What query/task should it satisfy?
    • What makes this page non-commodity: first-hand experience, data, benchmark, implementation detail, decision framework, original example, product evidence, or expert synthesis?
    • If nothing is distinctive, add evidence/value before adding more words.
  2. Make the answer retrievable.

    • Put a direct answer near its relevant question when that serves the reader; keep meaningful narrative context. Do not enforce a chunk size, word count or FAQ quota.
    • Use descriptive H2/H3 sections with stable IDs where the framework supports them.
    • Keep important facts in visible page content.
    • Use tables only when they genuinely clarify comparisons or dense data.
    • Add lists/process steps only where the information is procedural.
  3. Strengthen evidence and provenance.

    • Cite primary sources for changing technical/platform claims.
    • Add publication/update dates where meaningful.
    • Identify author/organization when useful for accountability.
    • Link benchmarks, datasets, receipts, changelogs or source repositories when claims depend on them.
    • Distinguish measured facts, interpretation and prediction.
  4. Build entity clarity.

    • Use the canonical product/project/person/organization name consistently.
    • State what the entity is and what category it belongs to in normal prose.
    • Link to canonical About/Product/Comparison pages.
    • Add appropriate Schema.org JSON-LD when the page maps cleanly to a supported type; do not invent types or stuff keywords.

Read the full file on GitHub · 98 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. 3d ago Changed · +14 lines 980985901df8
  2. 5d ago First seen · 84 lines · 86 tokens per session scan A 4775677e4249

Subscribe to this mod's changes

arwp-ai-search-content is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 1,279 once invoked, about $0.0004 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 2026-09-07.