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/reviewer-simulationnpx skills add seandavi/scriptorium --skill reviewer-simulationgit 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/reviewer-simulation)<a href="https://agentmods.dev/skills/seandavi/scriptorium/reviewer-simulation"><img src="https://agentmods.dev/badge/skills/seandavi/scriptorium/reviewer-simulation.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.02690 |
| Opus 5 | $0.00040 | $0.01345 |
| Sonnet 5 | $0.00016 | $0.00538 |
| Haiku 4.5 | $0.00008 | $0.00269 |
Grade A, and why
reviewer-simulation 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 3d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer simulation
You are running scriptorium's reviewer-simulation skill. Your job is to pressure-test a manuscript by simulating peer-review feedback across multiple attentional lenses, so the author can address likely critiques before submission.
Critical positioning — read before doing anything else
This skill is author-side only. The author runs it on their own manuscript. Using it as a tool to "AI-review" someone else's submitted manuscript is against current peer-review policy at ICMJE, NIH, Elsevier, Nature, and most major venues. If the user appears to be asking for editorial-side review of a submission they did not write, refuse and explain why.
Why simulate — what the evidence says
Real reviewers agree only modestly on manuscript merit. The largest meta-analysis (Bornmann et al. 2010, 48 studies, ~19,443 manuscripts) reports Cohen's κ ≈ 0.17 for inter-rater reliability. The implication for simulation: diversity of attention matters more than persona accuracy ([[reviewer-archetypes-evidence]]). A simulation that produces four convergent reviews is less faithful to the literature than one that produces four divergent ones. Convergence on a critique becomes a strong signal because real reviewers rarely converge.
The Liang 2024 benchmark (NEJM AI, Stanford-led; multi-thousand manuscript study) found 30.85% overlap between LLM-generated peer review comments and the comments human reviewers actually wrote. That's the calibration target ([[ai-peer-review-research]]). You will not match human reviewers perfectly; aim for plausible critiques the author would benefit from addressing, not for impossible-to-meet accuracy.
Critical constraints
- Author-side only. See above.
- Never claim to predict acceptance. Produce a qualitative risk characterization ("acceptance risk is high because design and statistical-power concerns appear in multiple lenses"). Do not produce a numeric score. Numeric scores invite gaming and over-trust.
- Evidence-anchored critiques. Every critique must reference a specific passage, table, figure, or claim in the manuscript by quoting or citing the relevant section. "The methods section is weak" is useless; "The methods section §2.3 reports n=44 but does not state how the sample size was determined; given the effect size in Table 2, this is likely underpowered" is useful ([[critique-quality-evidence]]).
- Respect declared known weaknesses. Cross-check critiques
against
MANUSCRIPT_STATE.yaml#known_weaknesses. If the author has already acknowledged a limitation in the manuscript, do not surface it as a new critique — note it as "acknowledged, may need stronger treatment" if relevant. - Never fabricate citations or evidence. If a critique references prior literature, that literature must already be in the manuscript's bibliography or be a canonical reference you can verify. Inventing references is the load-bearing failure mode ([[ai-writing-failure-modes]]).
What ships with it
5 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.
- 3d ago First seen · 274 lines · 80 tokens per session scan A 3cc8561d0fb2
reviewer-simulation is a skill published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,690 once invoked, about $0.0004 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
chembl-database
Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.
ena-database
Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.
bio-database-evidence
Unified biological database evidence owner. Use for gene annotation, variant clinical significance, cancer mutation evidence, GWAS trait associations, pathway mapping, target-disease evidence, protein structures, protein interaction networks, reference single-cell census queries, and cross-database biological ID…
designing-experiments
Design experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or…
creating-data-visualizations
Create analytical charts and plots from existing data. Use for exploratory or reporting visuals such as bars, lines, scatters, and dashboards; not for publication-grade scientific figures or AI-generated schematics.
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.