website-studio-skill AGENTS.md

Repository instructions for a portable website-studio skill, covering its working rules and checks before release.

In plain words
What is it for?
Use them when editing, testing, packaging, or reviewing the website-studio skill.
Why use it?
They give coding agents consistent rules for keeping the skill portable, safe, and verifiable.

Instructions file for CodexOpenCode

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 instructions/do-fei/website-studio-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/Do-fei/website-studio-skill

Made for: Codex, OpenCode.

Per session 234 This file is loaded in full into every session.
When invoked 234 The same file — it is already loaded in full.
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 $0.00234 $0.00234
Opus 5 $0.00117 $0.00117
Sonnet 5 $0.00047 $0.00047
Haiku 4.5 $0.00023 $0.00023

Measured yesterday against content hash 04b07abd55cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

website-studio-skill AGENTS.md 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.

AGENTS.md · 36 lines

What it actually says

Repository instructions

This repository contains one portable Agent Skill: website-studio.

Working rules

  • Keep SKILL.md concise and route detailed guidance into one-level-deep files.
  • Preserve the cross-agent core. Do not depend on vendor-only frontmatter or tools.
  • Do not add binary media, third-party brand assets, fonts, photos, audio, or video.
  • Use relative paths inside the Skill and keep every referenced file present.
  • Do not claim a client, deployment, browser flow, or public URL was tested without direct evidence.
  • When compatibility details change, cite the product's official documentation in docs/agent-setup.md.
  • Never include secrets, local machine paths, customer data, or copyrighted project media.

Verification

Run before every pull request or release:

npm test

For script syntax checks:

node --check scripts/*.mjs

For a release, commit first and then run:

npm run package:release

Extract the generated ZIP into a fresh directory and run npm test from the extracted website-studio folder.

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 First seen · 36 lines · 234 tokens per session scan A 04b07abd55cd

Subscribe to this mod's changes

website-studio-skill AGENTS.md is an instructions file published in the GitHub repository Do-fei/website-studio-skill (1 stars, last pushed 1mo ago), licensed MIT. It adds 234 tokens to every session, about $0.0012 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.