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 skills add seandavi/scriptorium --skill outlier-sentence-detectorgit clone --depth 1 https://github.com/seandavi/scriptoriumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/seandavi/scriptorium/outlier-sentence-detector)<a href="https://agentmods.dev/skills/seandavi/scriptorium/outlier-sentence-detector"><img src="https://agentmods.dev/badge/skills/seandavi/scriptorium/outlier-sentence-detector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/seandavi/scriptorium/outlier-sentence-detector"><img src="https://agentmods.dev/badge/skills/seandavi/scriptorium/outlier-sentence-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00094 | $0.04390 |
| Opus 5 | $0.00047 | $0.02195 |
| Sonnet 5 | $0.00019 | $0.00878 |
| Haiku 4.5 | $0.00009 | $0.00439 |
Grade A, and why
outlier-sentence-detector 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 8d ago.
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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outlier sentence detector
You are running scriptorium's outlier-sentence-detector skill. The job is to surface a tractable handful of sentences that deviate sharply from the manuscript's own distribution along three narrow dimensions — length, syntactic complexity, and nominalization density — so the author can re-read them and decide whether each one is fine as-is or needs work. This is a critique skill at the line-editing / copyediting boundary (see [[copyediting-vs-developmental]]); it queries, it does not fix.
Critical constraints — read before doing anything else
- This skill flags candidates for human review. It is not a quality
score. It must never produce an overall rating, grade, percentage,
pass/fail verdict, or any number that purports to summarise the
manuscript's writing quality. Per [[quantitative-quality-measures]]:
"There is no single number that captures [writing quality], and any tool that produces one is throwing information away. The useful operations are outlier flagging." Outlier flagging is what this skill does. Quality scoring is not.
- Thresholds are author-tunable via
meta.guidance_level. Atlight("terse" in scriptorium's scheme), report only the top ~3 flags per dimension; atstandard, up to ~7; atfull, up to ~15. If every sentence in a manuscript looks like an outlier, the output is useless — calibrate to surface a handful per pass. - Calibrate against the manuscript itself. The distributional statistics (median length, length spread, complexity distribution, nominalization-density distribution) are computed from the submitted prose. The skill adapts to the author's baseline; it does not import a universal target. Per [[quantitative-quality-measures]], universal-target tools (Flesch-Kincaid, SMOG, Coleman-Liau, BERTScore-as-a-gate) are theatre for scientific text; this skill is explicitly not that.
- Output is descriptive, not directive. Each flag is "worth re-reading because X", never "this sentence is bad" or "rewrite this sentence to be shorter". The author decides what to do.
- Never modify the manuscript. This skill emits a markdown report only.
- Use a sensible floor for short manuscripts. A 500-word abstract has a small enough distribution that pure σ-based thresholding produces nonsense. Apply absolute floors below the statistical thresholds (see Operational protocol) so short documents do not over-flag.
What ships with it
3 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.
- 8d ago First seen · 380 lines · 94 tokens per session scan A 94a5cf3e5956
outlier-sentence-detector is a skill published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 4,390 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
apple-container
Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…
imagen
Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for any purpose including UI mockups, icons, illustrations, diagrams, concept art, placeholder images, or visual representations.
pdlc-feature
An automated workflow for taking a new software feature from a description or requirements document through requirements, design, testing, implementation, review, and release preparation. It keeps one feature ID across the documents and requires tests before implementation.
pdlc-implement
A guarded coding workflow that implements a feature from its design document and existing tests, then checks the result. It requires tests to be written first, following TDD (test-driven development).
pdlc-standard
A manager for team standards stored under the project's standards directory, such as coding, API, or naming rules. It keeps one current document per topic and records changes in a separate change log.
pdlc-ui-design
A user-interface and user-experience design guide that turns an existing product requirements document into a page and interaction plan. A PRD is a document describing what a product or feature must do.