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 PangenomeAI/academic-skills-food-nutrition --skill food-reviewgit clone --depth 1 https://github.com/PangenomeAI/academic-skills-food-nutritionWrote 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/pangenomeai/academic-skills-food-nutrition/food-review)<a href="https://agentmods.dev/skills/pangenomeai/academic-skills-food-nutrition/food-review"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-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/pangenomeai/academic-skills-food-nutrition/food-review"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00173 | $0.02207 |
| Opus 5.5 | $0.00069 | $0.00883 |
| Sonnet 5.5 | $0.00035 | $0.00441 |
| Haiku 4.5 | $0.00017 | $0.00221 |
Grade A, and why
food-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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food-Review — Multi-Reviewer Peer Review for Food & Nutrition Manuscripts
Give the author the review a good food-science journal would return, from a panel rather than a single voice. Original work; architecture informed by open community peer-review skills (see the repo README Acknowledgements).
Modes
- full (default) — the whole panel: three domain reviewers + devil's advocate + format check, synthesized by the coordinator into an editorial decision.
- quick — coordinator + one blended reviewer pass; a fast readiness verdict.
- methodology — deep dive by
reviewer_methodologyonly. - re-review — re-assess a revised manuscript against the prior reports and the author's response, verifying each point was addressed.
Panel (dispatch via the Agent tool; reviewers run in parallel)
review_coordinator(editor-in-chief) — sets the target journal + scope, dispatchesknowledge_builder, then the reviewers, synthesizes their reports, resolves disagreement, and issues the decision.knowledge_builder— runs first: reads the manuscript's cited sources (Pathway A) and the field's key literature (Pathway B) into a shared knowledge base so the panel judges the science from knowledge, not impression.reviewer_methodology— design, statistics, reproducibility, validation.reviewer_domain— novelty, significance, scope fit, domain correctness (food/nutrition science).reviewer_integrity— data & citation integrity, food-safety/ethics, reporting completeness.devils_advocate— adversarial challenge to the paper's central claim.format_checker— formatting & reference-style compliance vs the target journal.
Ground the panel first — the knowledge base
Reviewers must understand the topic and its background before they critique it.
knowledge_builder runs before the reviewers and builds one knowledge base from:
- A — the manuscript's own citations: retrieve and read the full cited articles, extract what each actually shows, and audit whether it supports the claim it is attached to.
- B — the field's key literature: extract the manuscript's keywords and
research disciplines, search the literature for the field's key work
(may use the
food-researchfull reviewbranch for discovery/screening — but knowledge extraction only, no literature-review article).
What ships with it
13 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.
- agents/devils_advocate.md 1.6 KB
- agents/format_checker.md 1.7 KB
- agents/knowledge_builder.md 8.7 KB
- agents/review_coordinator.md 4.0 KB
- agents/reviewer_domain.md 2.0 KB
- agents/reviewer_integrity.md 1.9 KB
- agents/reviewer_methodology.md 2.0 KB
- references/editorial-decisions.md 1.5 KB
- references/ethics-integrity-checklist.md 1.7 KB
- references/quality-rubrics.md 1.6 KB
- references/report-format.md 7.2 KB
- references/review-criteria.md 3.0 KB
- references/word-review-comments.md 4.3 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 First seen · 135 lines · 173 tokens per session scan A b2fb1314e693
food-review is a skill published in the GitHub repository PangenomeAI/academic-skills-food-nutrition (38 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 2,207 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
paper-framework-figure-studio-pro
Human-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDIDATE-IMAGE. Use for paper-grounded architecture, pipeline, method overview, agent workflow, system/data-flow, and mechanism figures with generated raster first-round/formal candidates, reviewer-first-glance…
paper-polish-pipeline
Staged, diagnosis-driven academic paper polishing pipeline (bilingual 中文/English). Use to revise a paper from rough draft to final submission across ordered stages: diagnose first, then optimize section by section, derive abstract/contributions from the revised body, polish the language to reduce AI-sounding phrasing…
nature-reviewer
A peer-review checklist that assesses a research paper from a referee’s point of view, including its novelty, importance, and technical soundness.
autofigure
Generate clean, EDITABLE vector figures (SVG + exact-size PDF) for research papers — method / architecture / pipeline / system-overview diagrams — with AutoFigure-Edit. Use whenever the user wants to create or vectorize a paper figure from a text description OR from a draft/screenshot/draw.io image: it generates a…
nature-academic-search
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use when the user needs coordinated multi-step…
nature-citation
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default.…