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 0-osp-onboardinggit 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/0-osp-onboarding)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/0-osp-onboarding"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/0-osp-onboarding/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/0-osp-onboarding"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/0-osp-onboarding.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 | $0.00020 | $0.02465 |
| Opus 5.5 | $0.00008 | $0.00986 |
| Sonnet 5.5 | $0.00004 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
0-osp-onboarding scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
.open-scholar-peer/mcp/.venv/bin/python -c "import urllib.request as u;r=u.Request('https://api.openalex.org/works?per-page=1',headers={'User-Agent':'open-scholar-peer'});u.urlopen(r,timeout=5).read(1);print('NET_OK')" 2 How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/0-osp-onboarding — Stage 0: Onboarding
Prepares the review environment. Recommended first — every later phase runs without it, on generic criteria and with no venue.
Activation
Invoke the osp-orchestrator skill (no domain persona needed for this step).
Opening block (print before step 1)
Render the opening block exactly as .agents/defaults/phase_block_template.md defines it — that
file holds the rail, the rules and the widths, and it is the only place they are written down.
This is phase 1 of 7 (onboarding); read the rail's state from session.json. Values:
DOING set the venue, find the paper, scaffold criteria
READS .brain/input/ whatever you put there
WRITES .brain/raw/00_review_guidelines.md
.brain/session.json
COST ~1 min, one web search
Steps
1. Read session state
- Read
.brain/session.json. If it is missing, write it yourself from the v2 schema and carry on — the installer's scripts are not kept in the user's project, so do not send them looking for one. - If
phases.onboarding.status == "completed"andqa_criteriais non-empty, ask the user whether to re-run (which would overwrite00_review_guidelines.mdand any pre-scaffolded05_qa_*.mdfiles). If they decline, exit.
2. Locate the paper and ensure a readable text version
- Check
.brain/input/for a paper file. Common extensions:.pdf,.md,.tex,.docx. - If empty, look in the project root as well — the installer tells the user to put the paper there.
Ignore
README,AGENTS,CLAUDEand similar. Show what you found and ask them to confirm. - Whenever the user points at a file, wherever it is, copy it into
.brain/input/yourself. The same applies to any supporting material they offer later. Never ask them to move a file by hand. - Always produce
.brain/input/paper.md(the canonical readable form):- If the original is
.md, ensure it's namedpaper.md(rename if necessary). - If the original is
.pdf/.docx/.tex, attempt conversion with themarkitdownMCP tool (convert_to_markdown). Save output to.brain/input/paper.md. - If
markitdownis unavailable, do not silently advance. A readable paper is the one input the protocol cannot work around. Tell the user so, and offer two routes: (a) install markitdown (uvx markitdown-mcp --helpconfirms it is fetchable), or (b) hand over a markdown conversion of their own. Wait for one of them. This and the same guard in/1-osp-summaryare the only two places in Open ScholarPeer that stop. Everything else recommends and carries on.
- If the original is
- Save
paper.path(original) andpaper.parsed_path(the canonical.brain/input/paper.md) intosession.json.
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 · 172 lines · 20 tokens per session scan A 7f6a1c72f81c
0-osp-onboarding is a skill published in the GitHub repository amirkiarafiei/open-scholar-peer (48 stars, last pushed 12d ago), licensed MIT. It adds 20 tokens to every session and 2,465 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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 …