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.
npx agentmods add skills/seandavi/scriptorium/initnpx skills add seandavi/scriptorium --skill initgit clone --depth 1 https://github.com/seandavi/scriptoriumWhat 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 | $0.00099 | $0.04176 |
| Opus 5 | $0.00049 | $0.02088 |
| Sonnet 5 | $0.00020 | $0.00835 |
| Haiku 4.5 | $0.00010 | $0.00418 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init: conversational MANUSCRIPT_STATE.yaml bootstrap
You are running scriptorium's init skill. Your job is to walk an
author through populating MANUSCRIPT_STATE.yaml — the shared editorial
state every scriptorium skill reads. This is the conversational
counterpart to the CLI's scriptorium init <dir>: the CLI scaffolds
the file with comments; you fill it in with the author's actual
intent.
Invocation discipline
Invoke this skill explicitly when the author asks to set up scriptorium
on a manuscript that does not yet have a MANUSCRIPT_STATE.yaml, or
has only a partial one. Do not invoke it as a follow-up to another
skill without the author asking. If the author has already populated
the file thoroughly, the skill should detect that and exit cleanly
rather than re-asking everything.
Critical constraints — read before doing anything else
- Never invent fields not in the schema. The canonical schema is
schemas/manuscript-state.schema.jsonin the scriptorium install (also bundled with the plugin). Read it; treat it as the source of truth for which fields exist and what values they accept. - Never silently overwrite existing values. If
core_claimsalready has three entries, do not propose four new ones. Ask whether to add to, replace, or leave the existing list. - Always validate before writing. Run
scriptorium validateagainst the proposed file content (or run the schema check in-band) before persisting. Surface validation errors as conversational prompts, not as failures. - Be skippable at every stage. The author may want to fill only
a few fields and leave the rest empty for later. Always offer to
"skip the rest" — the file remains valid as long as the required
fields (
project.title,project.target_type,document_phase.current) are present. - Preserve template comments for empty fields. When a field is left blank, the output should still carry the CLI template's comment scaffolding so the author can fill it in later without guessing the schema.
What ships with it
4 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.
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 · 382 lines · 99 tokens per session scan A 870961fe1a80
init is a skill published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 4,176 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 2026-08-31.
Other skills, from other repositories
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
super-design
Use when the user asks you to build, style, theme, refine, audit, or recreate UI — or uploads a screenshot to rebuild. Reads DESIGN.md as a closed token layer, detects the project's framework (Tailwind v4/v3, ShadCN, MUI, Radix, Geist), and enforces production design rules (tokens only, full state matrix, WCAG 2.2 AA…
deep-modules
Measures module depth: whether the interface is simple relative to the implementation behind it. Use when an interface has too many parameters or methods, many small classes each do too little, or methods just forward calls. Not for whether adjacent layers provide different abstractions (use abstraction-quality) or…
red-flags
Scans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report. Use when reviewing a PR against a comprehensive checklist, evaluating unfamiliar code, or when the user asks for a red flags scan. Not for diagnosing why code feels complex (use…
comments-docs
Reviews comment quality and documentation practices: the four comment types, comments-first workflow, and comment rot. Use when reviewing comments or docs, when comments just repeat the code, or when something is hard to describe in a sentence. Not for naming or code obviousness (use naming-obviousness).