scriptorium

A documentation-writing tool based on Diátaxis, a method that separates docs into tutorials, task guides, reference material, and explanations. It also checks Markdown formatting against the CommonMark standard.

In plain words
What is it for?
It helps write, place, and format technical documentation, such as tutorials, how-to guides, reference pages, and conceptual explanations.
Why use it?
It helps decide what kind of document you are writing and prevents documents from mixing different purposes or containing invalid Markdown.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add backchainai/backchain-plugins
agentmods
npx agentmods add plugins/backchainai/backchain-plugins/scriptorium
Clone the repo
git clone --depth 1 https://github.com/backchainai/backchain-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

scriptorium 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.

scriptorium/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "scriptorium",
  "description": "Diataxis-grounded documentation authoring and placement. Routes a document to one of the four Diataxis modes (tutorial, how-to guide, reference, explanation), writes it under that mode's constraints, and checks its markdown form against CommonMark 0.31.2.",
  "version": "0.1.0",
  "author": {
    "name": "Chris Krough",
    "email": "[email protected]",
    "url": "https://dev.krough.org"
  },
  "license": "Apache-2.0",
  "keywords": [
    "diataxis",
    "documentation",
    "commonmark",
    "technical-writing",
    "agentskills"
  ],
  "category": "productivity",
  "repository": "https://github.com/backchainai/backchain-plugins",
  "homepage": "https://github.com/backchainai/backchain-plugins/tree/main/scriptorium"
}
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 · 22 lines scan A 2cefe76511ff

Subscribe to this mod's changes

scriptorium is a plugin published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 26d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

unslop

Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…

imisic/claude-marketplace · not measured

claude-code-plugin

Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.

Prismer-AI/PrismerCloud · not measured

skillcheck-free

Validates Claude Code SKILL.md files against 25 contract rules including structure, triggers, anti-patterns, and naming. Works with Claude Code, Claude Desktop/Web, and Cursor.

olgasafonova/SkillCheck-Free · not measured

techwolf-ai-first

Plugin marketplace listing 8 plugins: content-studio, ai-firstify, people-management, techwolf-brand-kit, knowledge-base.

techwolf-ai/ai-first-toolkit · not measured

people-management

AI-augmented management tooling for people managers. Surfaces the right context at the right time: before meetings, during 1:1 prep, when triaging messages, or reviewing customer status. Adapts to your org's performance and management frameworks. Augments managers, never automates.

techwolf-ai/ai-first-toolkit · not measured

tool-build-kit

Build an MCP server and bundle your tools into a shareable plugin, end to end. Two skills: build-mcp scaffolds one server; build-plugin packages skills, hooks, agents, and MCP servers into an installable plugin and ships it via a marketplace. Both branch on audience (personal, org, public).

techwolf-ai/ai-first-toolkit · not measured