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 hdu-ailab/EasyResearch --skill peer-reviewgit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWrote 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/hdu-ailab/easyresearch/peer-review)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/peer-review"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/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/hdu-ailab/easyresearch/peer-review"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/peer-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.01614 |
| Opus 5 | $0.00017 | $0.00807 |
| Sonnet 5 | $0.00007 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00161 |
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 10d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Review
Adapted from K-Dense for EasyResearch's independent Review Agent, immutable
reviews/ artifacts, Search-only nested dispatch, and no-source-edit boundary.
Scope And Authority
Review an explicitly supplied Markdown and/or TeX manuscript source against the supplied material package, accepted experiment evidence, figures/tables, venue requirements, and prior specialist handoffs. A PDF is never the sole manuscript input. Do not reconstruct or infer source from a PDF inside Review.
The dispatch must carry authorization to process the material through the currently configured model/provider and enough scope to identify confidentiality, venue, conflict, or policy constraints. Never ask the user directly. When source, authorization, venue policy, or critical evidence cannot be derived, preserve usable findings and return a blocked handoff for the Research Assistant.
Review supports an accountable human author/reviewer. It does not submit a review, contact an editor, upload confidential material, delete files, provide a publication decision, or certify scientific/ethical compliance.
Artifact Boundary
Every Review run or continuation creates a new immutable report:
reviews/review_report-YYYYMMDD-HHmmss-SSS.md
Write complete report content to a unique
reviews/.draft-review_report-<UUID>.md, then use
the absolute loaded specialist-handoff/scripts/publish_immutable.py path from
the exact session cwd with --directory reviews --prefix review_report to
publish it with atomic no-overwrite semantics. The helper
appends a numeric suffix on collision. Never overwrite a previous report and
never create a mutable review_report.md, latest pointer, or symlink. The Review
handoff names the exact report.
Review may write only its timestamped report and timestamped handoff. It must not modify manuscript, TeX, bibliography, experiment, result, or figure artifacts.
Inputs
Inspect only task-relevant supplied paths:
- authoritative
manuscript/manuscript.mdor explicit external Markdown; - relevant TeX/BibTeX source under
manuscript/latex/or an explicit layout; ref_papers/source.json,ref_papers/paper-notes.md, and readable source passages needed for claims;- exact accepted experiment record/results paths from the Experiment handoff;
- figure sources/exports and tables used by the manuscript;
- Writing and other specialist handoffs;
- current official venue/review/AI/confidentiality policy when applicable.
What ships with it
23 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.
- assets/citation_references_template.csv 196 B
- assets/claim_evidence_matrix_template.csv 745 B
- assets/reporting_checklist_template.csv 968 B
- assets/reporting_guidelines.json 13 KB
- assets/review_intake_template.json 1.3 KB
- assets/review_scaffold_template.md 2.6 KB
- assets/source_ledger.csv 8.9 KB
- assets/statistical_reproducibility_template.json 7.1 KB
- assets/study_profile_template.json 197 B
- LICENSE.upstream 1.0 KB
- references/common_issues.md 14 KB
- references/ethical_review_practice.md 10 KB
- references/reporting_standards.md 14 KB
- references/statistical_reproducibility.md 11 KB
- references/tool_reference.md 8.2 KB
- scripts/_common.py 14 KB runs code
- scripts/audit_citations.py 6.9 KB runs code
- scripts/audit_statistics_reproducibility.py 10 KB runs code
- scripts/generate_review_scaffold.py 2.6 KB runs code
- scripts/lint_review.py 7.4 KB runs code
- scripts/select_reporting_guidelines.py 13 KB runs code
- scripts/validate_claim_evidence.py 6.9 KB runs code
- scripts/validate_review_intake.py 15 KB runs code
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.
- 10d ago First seen · 171 lines · 34 tokens per session scan A 38bce54e8cc9
peer-review is a skill published in the GitHub repository hdu-ailab/EasyResearch (13 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,614 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
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of currentresearch with auditable repo…
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with…
explore-code
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together…
run-train
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized…