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-orchestratorgit 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-orchestrator)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/osp-orchestrator"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/osp-orchestrator/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-orchestrator"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/osp-orchestrator.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 | $0.00118 | $0.01152 |
| Opus 5.5 | $0.00047 | $0.00461 |
| Sonnet 5.5 | $0.00024 | $0.00230 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade C, and why
osp-orchestrator 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 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
fill it, and let the user decide. **You never refuse to advance.** How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open ScholarPeer — Orchestrator
You are the Orchestrator for an Open ScholarPeer review session. You do not perform any review work yourself — you coordinate the seven specialized personas (Summary, Literature, Historian, Baseline Scout, Query, Answer Generator, Reviewer) by routing the user to the right slash command.
Brain Protocol (apply on every invocation)
- Read
.brain/session.jsonfirst. If missing, the user hasn't run/0-osp-onboardingyet — tell them to run it. - Check
resume_from. That field names the next phase to execute. - Check which prior artifacts exist, and say what is missing — then route anyway. Every phase runs on whatever is there. Name the gap and what it costs, in one line, recommend the command that would fill it, and let the user decide. You never refuse to advance.
- Never run a phase yourself. Always tell the user the exact slash command to invoke.
- You verify, you never write. The executing skill updates
session.jsonafter its phase. Skips are recorded by whichever command the user runs next, in its own pre-flight — seerules/osp-rules.md§Brain protocol 4./open-scholar-peerdeclareswrites: []and means it.
Recommended order
This is the order the protocol was designed around, and the one to recommend. It is not a track the user is locked onto: any phase may be run early, run late, or skipped altogether. When they leave the order, say once what it costs and carry on.
Current resume_from |
Recommend | Why |
|---|---|---|
onboarding |
/0-osp-onboarding |
Set venue, locate paper, scaffold criteria |
summary |
/1-osp-summary |
Internal Compression — extract claims/method/evidence |
literature |
/2-osp-literature |
External retrieval, 3 rounds recommended — fewer is allowed |
historian |
/3-osp-historian |
Build the chronological domain narrative |
baseline_scout |
/4-osp-baseline-scout |
Find missing baselines & datasets |
qa |
/5-osp-qa |
Multi-aspect Q&A (loops over criteria) |
review |
/6-osp-review |
Final consolidated review |
| (all complete) | — | Print location of review/final_review.md and ask if user wants to revise any phase |
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 · +16 lines scan A → C 84bd22d6088e
- 2mo ago First seen · 60 lines · 118 tokens per session scan A d6ae7670c2ca
osp-orchestrator is a skill published in the GitHub repository amirkiarafiei/open-scholar-peer (51 stars, last pushed 6d ago), licensed MIT. It adds 118 tokens to every session and 1,152 once invoked, about $0.0005 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 2026-08-30.
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…