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/4-osp-baseline-scout)<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout/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/4-osp-baseline-scout"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout.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 | $0.00017 | $0.00517 |
| Opus 5 | $0.00009 | $0.00259 |
| Sonnet 5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
4-osp-baseline-scout 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
/4-osp-baseline-scout — Adversarial Baseline Audit
Acts as an adversarial auditor identifying baselines and datasets the authors should have compared against but didn't.
Activation
Invoke the osp-baseline-scout-agent skill.
Prerequisites
phases.literature.status == "completed". (historianis helpful but not strictly required — the Scout operates from the structured summary and the literature corpus.)
Resource notice
⚠️ Makes ~6-10 API calls to search for SOTA methods and benchmarks. Expect 1-2 minutes.
Steps
- Read
.brain/session.json,.brain/raw/01_structured_summary.md,.brain/raw/02_retrieved_literature.md. - Activate the
osp-baseline-scout-agentskill. - The skill identifies the paper's task and the baselines actually used (from the structured summary's Evidence section).
- The skill independently searches for state-of-the-art methods on the same task and benchmarks. Tools:
osp-mcp.search_*, native Web Search. Targeted queries include leaderboards, benchmark suites, and recent SOTA claims. - The skill produces a table of missing baselines and missing datasets with severity ratings (high/medium/low).
- Write
.brain/raw/04_missing_baselines.md. - Write
.brain/raw/04_missing_baselines.md. - Update
session.json:phases.baseline_scout.status = "completed"phases.baseline_scout.notes = "<N> missing baselines (<X> high); <M> missing datasets"resume_from = "qa"
User-facing report (print after completion)
── Baseline Audit complete ───────────────────────────────
Found <N> missing baselines (<X> high severity) and <M> missing datasets.
↳ .brain/raw/04_missing_baselines.md
Next: /5-osp-qa
──────────────────────────────────────────────────────────
Re-run behavior
Re-running overwrites 04_missing_baselines.md. Warn before doing so.
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 · 50 lines · 17 tokens per session scan A a75e92e3a863
4-osp-baseline-scout is a command published in the GitHub repository amirkiarafiei/open-scholar-peer (28 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 517 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
run-experiment
Execute experiments following the frozen plan with discipline enforcement.
write-paper
Write research paper with LaTeX modular structure and senior-level writing.
ars-plan
ARS academic-paper plan mode — Socratic chapter-by-chapter planning.
graphite-morphology-classify
Classify graphite in a cast-iron micrograph per ASTM A247 / ISO 945-1, quantify nodularity, and read the matrix — the single most diagnostic observation in a cast-iron case.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.