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.
/plugin marketplace add seandavi/scriptoriumnpx agentmods add plugins/seandavi/scriptorium/marketplacegit clone --depth 1 https://github.com/seandavi/scriptoriumGrade 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.
What it actually says
{
"name": "scriptorium",
"description": "Scriptorium: agentic operating system for scholarly writing. Citation audit, reviewer simulation, argumentative-flow analysis, manuscript-state initialization.",
"owner": {
"name": "Sean Davis",
"email": "[email protected]"
},
"plugins": [
{
"name": "scriptorium",
"source": "./",
"description": "Coordinated AI capabilities for manuscripts, grants, and reviews. Reads and writes a shared MANUSCRIPT_STATE.yaml so skills compose rather than each starting from scratch.",
"author": {
"name": "Sean Davis",
"email": "[email protected]"
},
"homepage": "https://github.com/seandavi/scriptorium",
"repository": "https://github.com/seandavi/scriptorium",
"license": "MIT",
"keywords": [
"scholarly-writing",
"scientific-writing",
"manuscripts",
"grants",
"peer-review",
"citation-audit",
"editorial",
"agentic"
],
"category": "writing"
}
]
}
What ships with it
1 file beside marketplace.json 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.
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.
- yesterday First seen · 34 lines scan A 281ce4a189ab
scriptorium is a plugin published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. 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.
Other plugins, from other repositories
clairvoyance-plugins
Plugin marketplace listing 1 plugin: clairvoyance.
clairvoyance
ESP for AI Coding — Agent skills on the philosophy of software design, grounded in decades of engineering experience.
super-design
Plugin marketplace listing 1 plugin: super-design.
super-design
Production-grade design system skill. Reads DESIGN.md, sets up theme tokens for Tailwind v3/v4, ShadCN, MUI, Radix, or Geist, and enforces consistent UI/UX via quality gates on every edit.
kotlin-lsp
Real-time Kotlin code intelligence for Claude — instant diagnostics, go-to-definition, find references, and type info via kotlin-language-server.
claude-superskills
Plugin marketplace listing 1 plugin: claude-superskills.