4-osp-baseline-scout

4-osp-baseline-scout is a command for Claude Code from amirkiarafiei/open-scholar-peer. It costs 17 tokens per session (517 once invoked), scanned A, original, MIT.

A research command for finding baselines and datasets missing from a scientific paper's comparisons. A baseline is another method used as a reference, while a dataset is a collection of examples used for evaluation.

In plain words
What is it for?
Use it in the fourth phase of an OSP review to audit a paper's evidence, search for relevant methods and benchmarks, and record missing comparisons with severity ratings.
Why use it?
It checks whether the authors compared their work with relevant recent methods and benchmarks, including state-of-the-art results, or the best known results for a task.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it in the fourth phase of an OSP review to audit a paper's evidence, search for relevant methods and benchmarks, and record missing comparisons with severity ratings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout
Install

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.

Clone the repo
git clone --depth 1 https://github.com/amirkiarafiei/open-scholar-peer

Made for: Claude Code.

Wrote 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.

agentmods badge for 4-osp-baseline-scout

README.md
[![agentmods](https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout/github.svg)](https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/4-osp-baseline-scout)
Your own site
<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.

agentmods 80×15 button for 4-osp-baseline-scout

Your own site · 80×15
<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>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash a75e92e3a863, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

extensions/.claude/commands/4-osp-baseline-scout.md · 50 lines

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". (historian is 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

  1. Read .brain/session.json, .brain/raw/01_structured_summary.md, .brain/raw/02_retrieved_literature.md.
  2. Activate the osp-baseline-scout-agent skill.
  3. The skill identifies the paper's task and the baselines actually used (from the structured summary's Evidence section).
  4. 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.
  5. The skill produces a table of missing baselines and missing datasets with severity ratings (high/medium/low).
  6. Write .brain/raw/04_missing_baselines.md.
  7. Write .brain/raw/04_missing_baselines.md.
  8. 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.

Changes

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.

  1. 12d ago First seen · 50 lines · 17 tokens per session scan A a75e92e3a863

Subscribe to this mod's changes

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.