arwp-adaptive-upgrade

arwp-adaptive-upgrade is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 77 tokens per session (748 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a website audit into a list of specific, evidence-backed changes, with targets, implementation steps, checks, and measurement signals. It also records when supporting knowledge needs to be reviewed again.

In plain words
What is it for?
Use it to plan website improvements related to search visibility, generative search, citations by AI systems, and measurement after an audit.
Why use it?
It replaces a broad score with concrete changes tied to a real site and its goals. This helps teams decide what to fix first and verify whether the changes had the intended effect.

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-upgrade.mjs site https://example.com/ \.

Good fit Use it to plan website improvements related to search visibility, generative search, citations by AI systems, and measurement after an audit.

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-adaptive-upgrade

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-adaptive-upgrade

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-adaptive-upgrade"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-adaptive-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 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 $0.00077 $0.00748
Opus 5 $0.00039 $0.00374
Sonnet 5 $0.00015 $0.00150
Haiku 4.5 $0.00008 $0.00075

Measured 3d ago against content hash dff6dbfc65b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arwp-adaptive-upgrade 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-adaptive-upgrade/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP Adaptive Upgrade

Use this skill after or together with the Growth Loop when the user expects concrete changes to a target website.

Goal

Translate current evidence into:

site state → applicable practice → exact target → change recipe → verification → measurement → review

Do not emit a generic 0–100 GEO score.

Workflow

  1. Identify the target site's real vertical(s) and goals. Do not classify a normal site as research-dataset unless a genuine reusable/distributable corpus exists.
  2. Run or reuse the Growth Plan and vertical evidence.
  3. Compile the Adaptive Upgrade Graph:
node bin/arwp-upgrade.mjs site https://example.com/ \
  --vertical=<vertical> \
  --goals=search,generative-search,ai-citations,measurement

or:

node bin/arwp-upgrade.mjs compile arwp-growth.json \
  --verticals=<verticals> \
  --goals=<goals> \
  --output=arwp-upgrade.json
  1. Review knowledgeState. Any review-due pack must have its upstream primary source rechecked before implementation.
  2. Work in dependency/priority waves. Fix P0 eligibility before optional acquisition or experimental agent surfaces.
  3. Respect the automation class:
    • mechanical: deterministic change may be suitable for bounded automation after authorization;
    • grounded-template: fill only facts already verified in the target repository/site;
    • policy-gated: require publisher decision;
    • editorial: do not manufacture expertise, experience, claims or data;
    • owner-platform: require authenticated platform evidence;
    • runtime: require browser/task evaluation.
  4. For repository implementation, record the exact files/surfaces changed and run the site's own tests/build plus the recommendation verification contract.
  5. After verification, capture owner/runtime outcome evidence separately. Never treat a successful implementation check as proof of ranking or citation impact.
  6. Keep/revise/revert/retire the recommendation and preserve negative results.

Dataset activation

Read the full file on GitHub · 78 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 First seen · 78 lines · 77 tokens per session scan A dff6dbfc65b9

Subscribe to this mod's changes

arwp-adaptive-upgrade is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 748 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 2026-09-08.

Related

Other skills, from other repositories