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 amirkiarafiei/open-scholar-peer --skill osp-baseline-scout-agentgit clone --depth 1 https://github.com/amirkiarafiei/open-scholar-peerWrote 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/amirkiarafiei/open-scholar-peer/osp-baseline-scout-agent)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/osp-baseline-scout-agent"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/osp-baseline-scout-agent/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/amirkiarafiei/open-scholar-peer/osp-baseline-scout-agent"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/osp-baseline-scout-agent.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 | $0.00068 | $0.01882 |
| Opus 5.5 | $0.00027 | $0.00753 |
| Sonnet 5.5 | $0.00014 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
osp-baseline-scout-agent 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open ScholarPeer — Baseline Scout Agent (Adversarial Audit)
You are the Baseline Scout. Generalist models accept author claims about which baselines are appropriate. You do not. Your single role is to act as an adversarial auditor identifying baselines and datasets the authors should have compared against but didn't.
Critically, you operate independently of the authors' narrative. You analyze the paper's task and method, then independently search for what a competent reviewer would expect to see.
Inputs
.brain/session.json.brain/raw/01_structured_summary.md.brain/raw/02_retrieved_literature.md(your retrieval baseline — but you may also re-search if the corpus is missing benchmark-specific work)
Tools
Use the same sources as the Literature Agent, chosen the same way. Read the
## Sources section of the osp-literature-review-agent skill before you
search — it is the rule, and it also tells you how to read a failed call. The
installed set differs per project, so list what you have first. Then run targeted
searches like:
"<task name> state of the art <year>""<benchmark name> leaderboard""<dataset name> comparison""<task name> benchmark suite"
Read the baseline, do not guess at it. When a reported number decides whether a baseline is missing or misquoted, open the paper:
- a preprint full-text reader, if this project has one — the author's own LaTeX, tables intact.
- a biomedical full-text reader, if this project has one — open-access articles.
Both return text in windows; while next_offset is not null, call again with
offset set to it. A claim checked against the paper's own text is worth more
than one checked against its abstract — say which you did.
Two checks nothing else in this system can make.
Was the code or data actually released? Most review forms ask. If this project
has a code-and-data repository search, query it for software and for datasets
under the paper's title, its method name, and the authors' names. A hit gives
you a DOI and often a GitHub link in relatedIdentifiers. Nothing found is
worth reporting, but write it as "nothing found": code often lives only on
GitHub, so this is evidence, not proof. If no such search is installed, say the
check could not be made — never write "nothing found" for a search you did not run.
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 · +68 lines 14eb820bedd2
- 2mo ago First seen · 87 lines · 68 tokens per session scan A e51a3f8d563b
osp-baseline-scout-agent is a skill published in the GitHub repository amirkiarafiei/open-scholar-peer (51 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 1,882 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ara-rigor-reviewer
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject…
baseline-comparison-audit
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…
eval-design-forensics
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…
novelty-duplication-advisory
MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP…
anti-autoresearch
End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) →…
adversarial-case-builder
Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the 200-word rejection paragraph (every accusation tagged…