What is 1-osp-summary?

A command for the first summary stage of a paper-review workflow. It extracts a research paper's main claims, method, and evidence into a structured summary for later stages.

Use it to summarise a paper after review-session setup, using an existing text file or converting a PDF, DOCX, or LaTeX source into readable text.

It gives later reviewers a consistent description of the paper and checks that readable paper text is available before processing begins. bioRxiv, journals, and other sources may provide papers as PDFs, but this workflow needs their text converted first.

1-osp-summary — Command for Claude Code by amirkiarafiei

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/1-osp-summary/github.svg)](https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/1-osp-summary)

Your own site

<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/1-osp-summary"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/1-osp-summary/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/amirkiarafiei/open-scholar-peer/1-osp-summary"><img src="https://agentmods.dev/badge/commands/amirkiarafiei/open-scholar-peer/1-osp-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 788 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00788
Opus 5	$0.00007	$0.00394
Sonnet 5	$0.00003	$0.00158
Haiku 4.5	$0.00001	$0.00079

Measured 11d ago against content hash a136ef944176, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

1-osp-summary 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 11d 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/1-osp-summary.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/1-osp-summary — Internal Compression

Extracts the paper's claims, method, and evidence into a structured summary Ŝ that downstream personas rely on.

Activation

Invoke the osp-summary-agent skill. The agent assumes the Summary Agent persona and follows that skill's protocol exactly.

Prerequisites

phases.onboarding.status == "completed" in session.json. If not, refuse and tell the user to run /0-osp-onboarding.

Hard input guard (run BEFORE invoking the persona)

The Summary Agent depends on having a readable text representation of the paper. PDF/DOCX/TEX in .brain/input/ is not enough — silent downstream failures are the #1 risk if the agent receives a binary path.

Before activating the skill, verify in this order:

.brain/input/paper.md exists and is readable — ideal case, proceed.
.brain/input/paper.md is missing but a PDF/DOCX exists — try to convert it now using the markitdown MCP tool (markitdown.convert). Save the result to .brain/input/paper.md. Update session.json.paper.parsed_path.
markitdown MCP is unavailable AND only a PDF/DOCX is present — refuse to proceed. Print a clear error:

Paper at .brain/input/<file> is in a binary format and markitdown MCP is not available. Either: (a) install markitdown: uvx markitdown-mcp (verify with uvx --version), or (b) convert the paper manually and place the markdown at .brain/input/paper.md, or (c) confirm your host tool can read this format natively (e.g. Claude Code reads PDFs) and re-run with --force-binary if exposed by the workflow.
Nothing in .brain/input/ — refuse and route to /0-osp-onboarding.

Do NOT silently proceed with a PDF path on the assumption that the host tool will handle it. Even if it can, the conversion result becomes part of the audit trail and must be in .brain/input/paper.md.

Steps

Run the hard input guard above.
Read .brain/session.json and .brain/input/paper.md (the validated markdown produced or verified by the guard).
Activate the osp-summary-agent skill — it owns the extraction protocol (claims, method, evidence) and the output format.
The skill writes .brain/raw/01_structured_summary.md.
The skill writes .brain/raw/01_structured_summary.md.
The skill updates session.json:
- phases.summary.status = "completed"
- phases.summary.completed_at = <now>
- phases.summary.notes = "<N> claims, <M> evidence items, method identified"
- resume_from = "literature"

Read the full file on GitHub · 62 lines

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.

11d ago First seen · 62 lines · 14 tokens per session scan A a136ef944176

Subscribe to this mod's changes

1-osp-summary is a command published in the GitHub repository amirkiarafiei/open-scholar-peer (27 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 788 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.

Research academic-paper-review ai-agents ai-peer-review peer-review research-paper research-tool

1-osp-summary

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/1-osp-summary — Internal Compression

Activation

Prerequisites

Hard input guard (run BEFORE invoking the persona)

Steps

What this file has done since we first saw it

Other commands, from other repositories

ars-mark-read

ars-cache-invalidate

ars-unmark-read

ars-revision-coach

ars-disclosure

ars-rebuttal-audit