arwp-target-transformation

arwp-target-transformation is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 92 tokens per session (928 once invoked), scanned A, original, Apache-2.0.

A workflow that turns approved website recommendations into specific, controlled repository changes. It links each change to an exact file, its inputs, before-and-after checks, verification, and rollback information.

In plain words
What is it for?
It is for preparing deterministic website edits after the target repository and the required verification conditions are known.
Why use it?
It reduces the risk of changing the wrong file or applying an unsupported recommendation automatically.

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-transform.mjs compile adaptive-upgrade.json target-transform-spec.json --output=transform.bundle.json.

Good fit It is for preparing deterministic website edits after the target repository and the required verification conditions are known.

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-target-transformation

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-target-transformation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-target-transformation"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-target-transformation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 928 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 $0.00092 $0.00928
Opus 5 $0.00046 $0.00464
Sonnet 5 $0.00018 $0.00186
Haiku 4.5 $0.00009 $0.00093

Measured 3d ago against content hash b2d58fb5aacd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

arwp-target-transformation 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-target-transformation/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP Target Transformation

Use this skill after arwp-adaptive-upgrade has answered what should change and the next job is resolve and deliver the exact repository change.

Goal

Turn applicable, current ARWP recommendations into a small deterministic change set with:

recommendation → exact file → grounded inputs → before digest → after digest → verification → rollback/PR

Do not treat an upgrade recipe as mutation authority.

Workflow

  1. Load the Adaptive Upgrade graph. Reject any recommendation whose knowledgeState is review-due until the upstream guidance is reviewed again.

  2. Inspect the target repository. Resolve the actual source files that own the public behavior. Do not patch generated output if the source template/config should be changed instead.

  3. Classify mutation eligibility.

    • mechanical: may become deterministic if the exact target is known.
    • grounded-template: may become deterministic only after first-party facts are found and recorded as grounding evidence.
    • policy-gated, editorial, owner-platform, runtime: keep gated; do not turn them into executable operations.
  4. Resolve exact operations. Prefer one operation per file. Supported v0.1 operations are create-file, replace-file, replace-exact, insert-before-exact, and insert-after-exact.

  5. Pin preconditions. Capture the exact current file content or absence, the target base commit SHA, and an explicit allowedPaths list. Never use broad ** mutation permissions.

  6. Compile and simulate.

node bin/arwp-transform.mjs compile adaptive-upgrade.json target-transform-spec.json --output=transform.bundle.json
node bin/arwp-transform.mjs simulate transform.bundle.json

Read the gated-recommendations section before delivery. A large gated list is normal; the engine is designed to automate only what is safe and resolved.

  1. Deliver. Prefer production PR delivery for shared repositories:
GITHUB_TOKEN=... node bin/arwp-transform.mjs open-pr transform.bundle.json \
  --authorize=target-repository-transform-pr

Read the full file on GitHub · 82 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 · 82 lines · 92 tokens per session scan A b2d58fb5aacd

Subscribe to this mod's changes

arwp-target-transformation is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 928 once invoked, about $0.0005 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.