A search tool for finding research and policy documents in arXiv, PubMed, and policy collections. arXiv and PubMed are online research databases.

Use it to find papers, look up publication details, check how current a collection is, retrieve full documents as Markdown, and compare evidence.

It makes searches and document retrieval repeatable, with explicit filters and freshness checks rather than relying on an unclear web search.

ii-commons — Skill for Codex by Intelligent-Internet

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.

Any agent

npx skills add Intelligent-Internet/II-Commons-Skills --skill ii-commons

Clone the repo

git clone --depth 1 https://github.com/Intelligent-Internet/II-Commons-Skills

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/intelligent-internet/ii-commons-skills/ii-commons/github.svg)](https://agentmods.dev/skills/intelligent-internet/ii-commons-skills/ii-commons)

Your own site

<a href="https://agentmods.dev/skills/intelligent-internet/ii-commons-skills/ii-commons"><img src="https://agentmods.dev/badge/skills/intelligent-internet/ii-commons-skills/ii-commons/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/skills/intelligent-internet/ii-commons-skills/ii-commons"><img src="https://agentmods.dev/badge/skills/intelligent-internet/ii-commons-skills/ii-commons.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,466 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	$0.00041	$0.01466
Opus 5	$0.00020	$0.00733
Sonnet 5	$0.00008	$0.00293
Haiku 4.5	$0.00004	$0.00147

Measured 12d ago against content hash cd8cd3e89d1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ii-commons 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ii_commons.js), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

ii-commons — 100% identical, 0 lines differ

skills/ii-commons/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

II-Commons

Use this as the top-level router for II-Commons retrieval. The CLI can be run through npm:

npx @intelligentinternet/ii-commons --help
npx @intelligentinternet/ii-commons cutoff

It can also be installed globally:

npm install -g @intelligentinternet/ii-commons
ii-commons cutoff

When this skill is installed directly into an agent runtime, resolve the bundled client relative to this SKILL.md directory:

node scripts/ii_commons.js --help

Runtime and service:

Requires Node.js 18 or newer.
Requires outbound network access to commons.ii.inc.
Source repository: https://github.com/Intelligent-Internet/II-Commons-Skills. Prefer the latest installed version from that repository.
Web app and API token requests: https://commons.ii.inc/
Basic usage works without authentication. For higher usage limits, help the user request an API token and configure it with II_COMMONS_API_KEY or the local ii-commons config file when asked.

Routing

Prefer deterministic commands.

Use search, meta, markdown, and cutoff for exact filters, explicit evidence flow, and reproducible retrieval.
Build synthesis from deterministic search and read steps.

Push explicit time constraints into search.

When the user asks for "latest", "current", "recent coverage", corpus freshness, or whether data is up to date, run cutoff before search and state the relevant cutoff date before interpreting results.
Treat cutoff as the authoritative freshness boundary for each corpus.
Describe arXiv and PubMed freshness as daily-updated coverage to the latest available cutoff date. Use the reported cutoff date to ground the freshness claim.
For arXiv and PubMed, convert explicit time constraints into --start and --end search filters before running search. Do this for phrases such as "last N years", "past N years", "recent N years", "since YYYY", "after YYYY-MM", "before YYYY", and year ranges like "2023-2025".
Prefer server-side date filtering over searching broadly and filtering returned records by year. Post-filter by year only when the corpus or command lacks date filters.
Date filters use integer formats: YYYYMMDD for exact dates, YYYYMM00 for known year/month, and YYYY0000 for year-only constraints.
For "last N years" or "past N years", compute the start date from the current date. If cutoff reports an earlier corpus cutoff than the current date, cap --end to that corpus cutoff.
Mapping examples: "past two years" means --start <current date minus two years as YYYYMMDD> --end <current or cutoff date as YYYYMMDD>; "since 2024" means --start 20240000; "2023-2025" means --start 20230000 --end 20250000.

Read the full file on GitHub · 100 lines

Files

What ships with it

3 files 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.

12d ago First seen · 100 lines · 41 tokens per session scan A cd8cd3e89d1c

Subscribe to this mod's changes

ii-commons is a skill published in the GitHub repository Intelligent-Internet/II-Commons-Skills (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,466 once invoked, about $0.0002 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 arxiv cli daily-updated pmc policy pubmed

academic-research

Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…

Lingtai-AI/lingtai · 180 tokens

research-agent

Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls; includes an optional PubMed/arXiv standard-library helper.

ellmos-ai/skills · 36 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

ii-commons