A guide for adding and maintaining Scribe technical articles in React websites built with Next.js or Vite. Scribe is publishing infrastructure for website content, not a standalone content-management system.

Use it to author, convert, validate, or troubleshoot articles written in Markdown, MDX, JSX, or semantic HTML.

It helps keep the existing site's design and ownership intact while avoiding integration errors and unnecessary changes to the host application.

scribe — Skill by aetosdios27

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 skills/aetosdios27/scribe/cli

Any agent

npx skills add aetosdios27/scribe --skill cli

Clone the repo

git clone --depth 1 https://github.com/aetosdios27/scribe

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,133 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00044	$0.03133
Opus 5	$0.00022	$0.01566
Sonnet 5	$0.00009	$0.00627
Haiku 4.5	$0.00004	$0.00313

Measured 2d ago against content hash 569ec77ff206, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scribe 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 2d ago.

The scan reads SKILL.md. This mod also ships 51 executable files (src/bootstrap.test.ts, src/bootstrap.ts, src/content-paths.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to scribe — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/cli/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrating Scribe

Principle

Use Scribe as publishing infrastructure inside the website the user already owns. Preserve its routing, deployment, content files, fonts, colors, spacing, and identity.

The host owns visual design. Scribe owns publishing structure and behavior.

When a broad request says to install Scribe or make a blog better, the default result is the existing host design with stronger publishing mechanics. Proceed with that preservation contract; do not stop to ask how extensively to redesign the site. Ask only when the repository contains genuinely conflicting visual directions or the requested change would alter product identity.

Prefer ordinary Markdown and semantic HTML. Use Scribe-specific components only when richer semantics or metadata are genuinely required.

Treat unexpected integration workarounds as possible Scribe defects. Do not silently patch around them in the host application.

Scribe is not a CMS, hosted platform, website builder, rich-text editor, proprietary format, collaboration system, or replacement for React, Next.js, HTML, or MDX.

Scribe 0.1.0-beta is a public beta. Package versions may use prerelease SemVer identifiers while the API is still evolving.

Inspect before changing

Read the host repository instructions.
Identify React, Next.js or Vite, MDX versions, package manager, component-map location, global stylesheet entry, theme mechanism, and production build command.
Inspect the host’s fonts and CSS tokens. Reuse them; do not impose a Scribe font or redesign the site.
Find one representative article containing headings, code, tables, and images.
Confirm installed Scribe packages and keep their prerelease versions aligned.

Expected packages are @scribe-sdk/react, @scribe-sdk/styles, @scribe-sdk/mdx, and development-only @scribe-sdk/cli. Read the installed Scribe README and SKILL.md before integrating. Depending on the installed package, these are available under paths such as node_modules/@scribe-sdk/react/README.md and node_modules/@scribe-sdk/react/SKILL.md. Use the packaged copies rather than relying on remembered APIs.

Read the full file on GitHub · 233 lines

Files

What ships with it

58 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2d ago First seen · 233 lines · 44 tokens per session scan A 569ec77ff206

Subscribe to this mod's changes

scribe is a skill published in the GitHub repository aetosdios27/scribe (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,133 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scribe, differing in 0 lines, and is treated as a copy.

Debugging Frontend Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens