synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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 synthetic-sciences/openscience --skill peer-reviewgit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/peer-review)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/peer-review"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/peer-review/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/synthetic-sciences/openscience/peer-review"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/peer-review.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 | $0.00110 | $0.01397 |
| Opus 5.5 | $0.00044 | $0.00559 |
| Sonnet 5.5 | $0.00022 | $0.00279 |
| Haiku 4.5 | $0.00011 | $0.00140 |
Grade A, and why
peer-review 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer review
A review's job is to tell the authors, and the editor, whether the evidence supports the claims, and what would have to change if it does not. It is not a summary, not a list of typos, and not an opinion about how interesting the topic is. Read everything, check what can be checked, and separate what blocks from what would help.
Non-negotiables
- Read the whole artifact including appendices, supplementary tables, and code when it is provided. A review of the first eight pages is not a review.
- Check, do not just read. Recompute a number when the inputs are there; rerun a provided analysis; compare a figure to the table it summarizes; check that the test matches the design (paired vs unpaired, multiple comparisons, dependence).
- BLOCKING or OBSERVATION, for every point. Blocking means the central claim is not supported as written: leakage, a wrong test, an unfair baseline, a result that does not appear in the data, a claim outside the study's scope. Observations improve the paper but do not change whether it is right.
- Locate every issue. Section, page, table, figure, equation, line. "The statistics are weak" is not a finding; "Table 2 reports p < 0.05 from a t-test on 3 seeds per condition without correction across 12 comparisons" is.
- Calibrate. The recommendation follows from the blocking list, not from taste.
references/calibration.mdandreferences/scoring-rubric.mddefine the scale. - Constructive and specific. Each blocking issue names the fix or the experiment that would resolve it. Tone stays neutral; the authors are colleagues.
Workflow
- Read fully; write the paper's claims in your own words (three lines).
- For each claim: the evidence offered, and whether it supports the claim as worded.
- Methods and statistics check (
references/statistical-pitfalls.md,references/common-issues.md). - Figures, tables and reporting check (
references/paper-mechanics.md,references/reporting-standards.md). - Reproducibility and ethics check.
- Classify, calibrate, write the report.
What ships with it
10 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.
- references/calibration.md 7.5 KB
- references/common-biases.md 11 KB
- references/common-issues.md 19 KB
- references/evidence-hierarchy.md 13 KB
- references/logical-fallacies.md 18 KB
- references/paper-mechanics.md 9.8 KB
- references/reporting-standards.md 10 KB
- references/reviewer-expectations.md 16 KB
- references/scoring-rubric.md 8.7 KB
- references/statistical-pitfalls.md 16 KB
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.
- 1mo ago Changed · +5 lines 041ac04194b1
- 1mo ago Changed · +2 tokens per session 89bbbd5061ee
- 1mo ago First seen · 107 lines · 108 tokens per session scan A c22f86dcb590
peer-review is a skill published in the GitHub repository synthetic-sciences/openscience (4,025 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 1,397 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
songsee
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
arxiv
Search arXiv papers by keyword, author, category, or ID.
research-paper-writing
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
paper-plot-stub
Plot a results CSV (x, ybaseline, yours) as a two-line matplotlib chart and write a PDF. Demo-only.
knowledge-extension-ecosystem-lsp-code-intelligence
A codebase guide to LSP, the standard protocol behind editor features such as symbol queries, file diagnostics, and language-aware code information.