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 claesbackman/AI-research-feedback --skill review-paper-checksgit clone --depth 1 https://github.com/claesbackman/AI-research-feedbackWrote 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/claesbackman/ai-research-feedback/review-paper-checks)<a href="https://agentmods.dev/skills/claesbackman/ai-research-feedback/review-paper-checks"><img src="https://agentmods.dev/badge/skills/claesbackman/ai-research-feedback/review-paper-checks/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/claesbackman/ai-research-feedback/review-paper-checks"><img src="https://agentmods.dev/badge/skills/claesbackman/ai-research-feedback/review-paper-checks.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 | $0.00042 | $0.04004 |
| Opus 5 | $0.00021 | $0.02002 |
| Sonnet 5 | $0.00008 | $0.00801 |
| Haiku 4.5 | $0.00004 | $0.00400 |
Grade A, and why
review-paper-checks 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 12d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are coordinating a mechanical error check of an economics paper. You will run 3 agents in parallel and consolidate their output into a single list of concrete, fixable defects.
What this skill does: finds things that are wrong — misspellings, grammar errors, numbers that disagree between text and tables, terminology that drifts, cross-references that point to nothing, sentences that claim more than the evidence supports.
What this skill does not do: judge the contribution, evaluate the identification strategy, propose additional analyses, or issue a publication recommendation. Those are editorial judgments and belong to /review-paper-light (fast) or /review-paper (full). Do not let the agents drift into them, and do not add such judgments yourself when consolidating.
Phase 1: Discover the Paper
If a file path is provided in $ARGUMENTS, use it as the main LaTeX file. Otherwise, auto-detect:
- Use Glob with pattern
**/*.texto list all .tex files (exclude_minted-*,build/,output/). - Identify the main document among the .tex files containing
\documentclassor\begin{document}. If several candidates match, discard beamer slides and files whose name or folder suggests an old draft or a response letter (response*,letter*,slides*,old*,archive/, etc.), then choose the candidate with the largest include-graph. If still ambiguous, ask the user. - Read the main file and extract all
\input{},\include{}, and\subfile{}references (recursively) to build the paper's include-graph. - Read all component .tex files. The file list passed to the agents is exactly the main file plus its include-graph — do not pass .tex files the paper does not include (old drafts, response letters, slides, notes).
- Use Glob to find table files:
**/Tables/**/*.tex,**/tables/**/*.tex,**/Table/**/*.tex,**/table/**/*.tex, root-level*table*.texand*Table*.tex. Keep only tables that are\input{}/\include{}d from the include-graph. - Use Glob to find the bibliography:
**/*.bib. Keep only files named in a\bibliography{},\addbibresource{}, or\begin{thebibliography}block within the include-graph. If the references are typed directly into a .tex file, note that instead.
Record:
- Full path of each .tex file
- Full path of each referenced table .tex file and .bib file
- Paper title, authors, and abstract
If no table files are found, warn the user: "No table .tex files were found in standard locations. Agent B can only check consistency across the prose, not against table source files."
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.
- 12d ago First seen · 276 lines · 42 tokens per session scan A 331b07a1608f
review-paper-checks is a skill published in the GitHub repository claesbackman/AI-research-feedback (478 stars, last pushed 15d ago), licensed MIT. It adds 42 tokens to every session and 4,004 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…