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 open-scholar-peergit 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/open-scholar-peer)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/open-scholar-peer"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/open-scholar-peer/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/open-scholar-peer"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/open-scholar-peer.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 | $0.00703 |
| Opus 5.5 | $0.00008 | $0.00281 |
| Sonnet 5.5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade C, and why
open-scholar-peer 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.
5. **Recommend; never refuse.** The order below is the recommended one, not a lock. If the user asks for How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/open-scholar-peer — Stateless Dispatcher
This command is always available. It reads .brain/session.json and tells the user where they are in the review and which command to run next. It never executes review work itself.
Activation
Invoke the osp-orchestrator skill.
Steps
-
Read
.brain/session.json. If it is missing, OSP is not initialised here. Two cases, and neither should send the user hunting for a script that is not in their project:.brain/is absent as well — have them re-run the installer from this directory; it merges with their existing config rather than replacing it..brain/exists but the file does not — write it from the v2 schema yourself, then carry on.
-
Print the status block defined in
.agents/defaults/phase_block_template.md, labelledOPEN SCHOLARPEER. The rail is the whole point here — it answers "where am I" with no words. Values:STEPS onboard·summary·lit·history·baseline·qa·review VENUE <name> · <N> criteria PAPER <path, or "not yet loaded"> NOTE literature stopped at round 2 of 3, by choice NEXT /3-osp-historian the narrative (recommended) /5-osp-qa skip aheadNOTElists every phase whosestatusisskipped, plus any round or criterion left short; drop the label when there are none.NEXTrecommends first, then offers. -
Route based on
resume_from:resume_fromTell user to run Description onboarding/0-osp-onboardingSet venue, locate paper, scaffold criteria summary/1-osp-summaryInternal Compression — claims/method/evidence literature/2-osp-literatureExternal retrieval, up to 3 rounds — the user chooses historian/3-osp-historianBuild the chronological domain narrative baseline_scout/4-osp-baseline-scoutFind missing baselines & datasets qa/5-osp-qaMulti-aspect Q&A (loops over criteria) review/6-osp-reviewFinal consolidated review completed— Print location of .brain/review/final_review.mdand ask if any phase needs a re-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.
- 22d ago First seen · 57 lines · 19 tokens per session scan C a8fef7a8f59c
open-scholar-peer 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 703 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 …