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 1-osp-summarygit 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/1-osp-summary)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/1-osp-summary"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/1-osp-summary/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/1-osp-summary"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/1-osp-summary.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 | $0.00019 | $0.01081 |
| Opus 5.5 | $0.00008 | $0.00432 |
| Sonnet 5.5 | $0.00004 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade C, and why
1-osp-summary scanned grade C with 1 finding 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 22d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
that the venue is unknown. Mention `/0-osp-onboarding` once. Do not insist, and do not refuse. How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/1-osp-summary — Internal Compression
Extracts the paper's claims, method, and evidence into a structured summary Ŝ that downstream personas rely on.
Activation
Invoke the osp-summary-agent skill. The agent assumes the Summary Agent persona and follows that skill's protocol exactly.
Inputs — none of these is a gate
phases.onboarding.status == "completed"insession.json. If onboarding was skipped you have no venue and no review guidelines; extract the summary anyway, and record underNOTEand in Provenance that the venue is unknown. Mention/0-osp-onboardingonce. Do not insist, and do not refuse.
The one thing that cannot be worked around
Every other input in this protocol is optional. This one is not: with no readable text of the paper there is nothing to review, so this guard stops — and it is the only place in Open ScholarPeer that does.
PDF/DOCX/TEX in .brain/input/ is not enough on its own; a binary path handed to the agent is the
single biggest cause of silent downstream failure.
Before activating the skill, verify in this order:
.brain/input/paper.mdexists and is readable — ideal case, proceed..brain/input/paper.mdis missing but a PDF/DOCX exists — try to convert it now using themarkitdownMCP tool (convert_to_markdown). Save the result to.brain/input/paper.md. Updatesession.json.paper.parsed_path.markitdownMCP is unavailable AND only a PDF/DOCX is present — stop here, and say why in one line: there is no readable text to summarise. Print:Paper at
.brain/input/<file>is in a binary format andmarkitdownMCP is not available. Either: (a) install markitdown —uvx markitdown-mcp --helpconfirms it is fetchable; plainuvx markitdown-mcpstarts the server and waits, which looks like a hang — or (b) convert the paper manually and place the markdown at.brain/input/paper.md, or (c) if your host tool reads this format natively (Claude Code reads PDFs, for one), read it yourself, write the extracted text to.brain/input/paper.md, and re-run.- Nothing in
.brain/input/— stop here too; there is no paper. Point at/0-osp-onboarding, which will help locate it.
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.
- 22d ago First seen · 83 lines · 19 tokens per session scan C 7d48db4e7922
1-osp-summary is a skill published in the GitHub repository amirkiarafiei/open-scholar-peer (48 stars, last pushed 12d ago), licensed MIT. It adds 19 tokens to every session and 1,081 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
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…
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…
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) →…
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…
experiment-forensics
Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope…
proof-derivation-forensics
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …