3-osp-historian

3-osp-historian is a command for Claude Code from amirkiarafiei/open-scholar-peer. It costs 13 tokens per session (441 once invoked), scanned A, original, MIT.

A command for turning collected research papers into a chronological explanation of how a research subfield developed.

In plain words
What is it for?
Use it after literature retrieval to write the domain narrative, place the paper under review in that history, and update the research session.
Why use it?
It helps replace a disconnected list of papers with a timeline showing major approaches, turning points, and related earlier work.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after literature retrieval to write the domain narrative, place the paper under review in that history, and update the research session.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/amirkiarafiei/open-scholar-peer/3-osp-historian
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 3-osp-historian

README.md
[![agentmods](https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/3-osp-historian/github.svg)](https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/3-osp-historian)
Your own site
<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/3-osp-historian"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/3-osp-historian/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 3-osp-historian

Your own site · 80×15
<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/3-osp-historian"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/3-osp-historian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 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 $0.00013 $0.00441
Opus 5 $0.00006 $0.00220
Sonnet 5 $0.00003 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 12d ago against content hash 01f3726b5452, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

3-osp-historian 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/3-osp-historian.md · 46 lines

What it actually says

/3-osp-historian — Sub-Domain Historian

Compresses the retrieved literature into a chronological narrative that mimics a senior researcher's mental model of the sub-domain.

Activation

Invoke the osp-historian-agent skill.

Prerequisites

  • phases.literature.status == "completed" and 02_retrieved_literature.md exists.

Steps

  1. Read .brain/session.json, .brain/raw/01_structured_summary.md, .brain/raw/02_retrieved_literature.md.
  2. Activate the osp-historian-agent skill.
  3. The skill builds a chronological narrative grouped by inflection points (eras), each characterized by its dominant approach and what triggered the transition out.
  4. The skill places the paper under review in the narrative — same era it claims, or a different one — and identifies its closest precedents.
  5. Write .brain/raw/03_domain_narrative.md.
  6. Write .brain/raw/03_domain_narrative.md.
  7. Update session.json:
    • phases.historian.status = "completed"
    • phases.historian.notes = "<N> eras identified; paper placed in era <N>"
    • resume_from = "baseline_scout"

User-facing report (print after completion)

── Domain Narrative complete ─────────────────────────────
Mapped <N> historical eras; placed paper in era <E>.
Closest precedents: <2-3 bullet items>
↳ .brain/raw/03_domain_narrative.md
Next: /4-osp-baseline-scout
──────────────────────────────────────────────────────────

Re-run behavior

Re-running overwrites 03_domain_narrative.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 · 46 lines · 13 tokens per session scan A 01f3726b5452

Subscribe to this mod's changes

3-osp-historian is a command published in the GitHub repository amirkiarafiei/open-scholar-peer (28 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 441 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.