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.
git 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/commands/amirkiarafiei/open-scholar-peer/6-osp-review)<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/6-osp-review"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/6-osp-review/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/commands/amirkiarafiei/open-scholar-peer/6-osp-review"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/6-osp-review.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 | $0.00016 | $0.00571 |
| Opus 5 | $0.00008 | $0.00285 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
6-osp-review 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 12d 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.
What it actually says
/6-osp-review — Final Review Generation
Synthesizes the structured summary, retrieved literature, domain narrative, missing baselines, and verified Q&A pairs into a single consolidated review formatted to the venue's guidelines.
Activation
Invoke the osp-reviewer-agent skill.
Prerequisites
- All earlier phases completed:
summary,literature,historian,baseline_scout,qa. - All
05_qa_<slug>.mdfiles exist with 10 pairs each.
Steps
- Read all artifacts listed in the frontmatter.
- Activate the
osp-reviewer-agentskill. - The skill follows the structure dictated by
00_review_guidelines.md. If using the generic fallback, the structure is: Summary / Strengths / Weaknesses / Detailed comments per criterion / Questions for authors / Decision recommendation / Confidence. - The skill performs no new retrieval — it is decoupled from investigation, synthesis only.
- Write
.brain/review/final_review.md. - Write
.brain/review/final_review.md. - Update
session.json:phases.review.status = "completed"phases.review.notes = "Final review written; decision: <recommendation>"resume_from = "completed"
User-facing report (print after completion)
── Review complete ───────────────────────────────────────
Decision: <Reject | Major revision | Minor revision | Accept>
↳ .brain/review/final_review.md
To revise any phase, re-invoke its slash command.
──────────────────────────────────────────────────────────
Re-run behavior
Re-running overwrites final_review.md. Useful when the user wants to regenerate the review after revising an earlier phase (e.g., re-running /5-osp-qa for a single criterion). Warn before overwriting.
Pitfalls
- Do not introduce new findings. Every claim in the review must trace to a prior artifact.
- Do not invent citations. Every cited paper must be in
02_retrieved_literature.md. - Match the venue's tone and structure exactly. ICLR ≠ NeurIPS ≠ workshop.
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.
- 12d ago First seen · 52 lines · 16 tokens per session scan A 8864bb53cdb8
6-osp-review is a command published in the GitHub repository amirkiarafiei/open-scholar-peer (28 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 571 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
ars-mark-read
ARS /ars-mark-read — record a user-attested reading signal for one or more citation keys.
ars-cache-invalidate
ARS /ars-cache-invalidate — drop cached verification entries for a citation key.
ars-unmark-read
ARS /ars-unmark-read — rescind a user-attested reading signal for one or more citation keys.
ars-disclosure
ARS academic-paper disclosure mode — venue applicability/status bundle or policy-anchor render.
ars-revision-coach
ARS academic-paper revision-coach — peer-review roadmap or source-accounted real-committee response skeleton.
ars-rebuttal-audit
ARS academic-paper rebuttal-audit mode — QA an existing rebuttal draft against reviewer comments.