papers-batch-analyze

papers-batch-analyze is a skill for Claude Code, Codex from RipeMangoBox/BITE. It costs 97 tokens per session (1,806 once invoked), scanned A, original, MIT.

A batch research tool that reads a paper list from a CSV file or an Obsidian vault, a folder of linked Markdown notes, and divides it into smaller groups for analysis.

In plain words
What is it for?
It is for analyzing many research papers from a paper list, saving analysis notes in an Obsidian vault, and organizing the results for later lookup.
Why use it?
It removes the need to split a large paper list and track parallel analysis work by hand. It also gathers the resulting notes and refreshes the vault index when the batches finish.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ripemangobox/bite/papers-batch-analyze
Any agent
npx skills add RipeMangoBox/BITE --skill papers-batch-analyze
Clone the repo
git clone --depth 1 https://github.com/RipeMangoBox/BITE

Made for: Claude Code, Codex.

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 papers-batch-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/ripemangobox/bite/papers-batch-analyze.svg)](https://agentmods.dev/skills/ripemangobox/bite/papers-batch-analyze)
Your own site
<a href="https://agentmods.dev/skills/ripemangobox/bite/papers-batch-analyze"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/papers-batch-analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00097 $0.01806
Opus 5 $0.00048 $0.00903
Sonnet 5 $0.00019 $0.00361
Haiku 4.5 $0.00010 $0.00181

Measured 4d ago against content hash e4021727df54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

papers-batch-analyze 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/split_paper_list.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/papers-batch-analyze/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Paper Analysis

Use this skill to manage batch analysis from paper_list.csv. The managing agent coordinates batching and workers; the splitter script only creates batch CSV files and a manifest. It must not run LLM analysis.

Inputs

  • Default source: obsidian-vault/paper_list.csv
  • User override: any user-provided CSV path
  • Default batch size: 25
  • Default parallelism: 4 worker agents processing 4 batches at a time
  • Output batches: obsidian-vault/batches/<run_id>/batch_0001.csv, etc.

Expected CSV columns:

state,importance,paper_title,venue,project_link_or_github_link,paper_link,sort,pdf_path

Column notes:

Column Meaning
state Pipeline state. Analyze rows that are ready, normally Downloaded; skip analysised, checked, Skip, Missing, and blank states unless the user says otherwise.
importance Optional priority label such as S/A/B/C. Preserve it.
paper_title Paper title used for reporting and fallback naming.
venue Venue label, usually CVPR 2025, ICLR 2026, or arXiv YYYY.
project_link_or_github_link Project page, GitHub repo, or N/A.
paper_link Paper page such as arXiv/OpenReview/proceedings.
sort Source section/category label.
pdf_path Local PDF path. Prefer this exact path when analyzing.

Backward Compatibility

Use paper_list.csv terminology in this skill. If obsidian-vault/paper_list.csv is missing but an old obsidian-vault/analysis/paper_list.csv exists, do not blindly overwrite. Tell the user you found the legacy log and propose a reviewed copy/convert step:

cp obsidian-vault/analysis/paper_list.csv obsidian-vault/paper_list.csv

Before using the copied file, review the header and a few rows to confirm the columns match the expected paper_list.csv schema.

Manager Workflow

  1. Resolve the source CSV:
    • Use the user-provided path if supplied.
    • Otherwise use obsidian-vault/paper_list.csv.
    • If only legacy paper_list.csv exists, follow the reviewed migration step above before batching.
  2. Create batches:

Read the full file on GitHub · 164 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 164 lines · 97 tokens per session scan A e4021727df54

Subscribe to this mod's changes

papers-batch-analyze is a skill published in the GitHub repository RipeMangoBox/BITE (60 stars, last pushed 21d ago), licensed MIT. It adds 97 tokens to every session and 1,806 once invoked, about $0.0005 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.