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.
npx skills add iowarp/clio-kit --skill research-surveygit clone --depth 1 https://github.com/iowarp/clio-kitWrote 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.
[](https://agentmods.dev/skills/iowarp/clio-kit/research-survey)<a href="https://agentmods.dev/skills/iowarp/clio-kit/research-survey"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/research-survey/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.
<a href="https://agentmods.dev/skills/iowarp/clio-kit/research-survey"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/research-survey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00045 | $0.01338 |
| Opus 5.5 | $0.00018 | $0.00535 |
| Sonnet 5.5 | $0.00009 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
research-survey scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`fetch(target=...)` returns content through an ordinary MCP call when the client How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Survey
ArXiv exposes seven search tools. They are not variations on one another, and
defaulting to search_arxiv for every question is the main way this goes wrong.
Pick the search that matches the question
| The question | Tool |
|---|---|
| What exists on this topic | clio-arxiv:search_arxiv |
| Work by this person | clio-arxiv:search_papers_by_author |
| I know roughly the title | clio-arxiv:search_by_title |
| Papers whose content is about X | clio-arxiv:search_by_abstract |
| Everything in this field | clio-arxiv:search_by_subject |
| What has happened since | clio-arxiv:search_date_range |
| What is new in this field | clio-arxiv:get_recent_papers |
search_by_abstract is the one to reach for on a research question. Title search
finds papers that named the thing; abstract search finds papers that did it. For
any concept named inconsistently across a field, they return different sets.
Subject search needs the ArXiv category code (astro-ph.GA, cs.DC). Do not
guess one — an invalid category returns nothing, which reads like "no such work
exists".
Widen deliberately, not by repeating
A thin result set is a signal about the query, not the field. In order:
- Try
search_by_abstractif you used title search. - Try the field's other vocabulary. Terminology differs across communities for the same idea.
- Take the closest paper and run
clio-arxiv:find_similar_paperson it. This works from the paper's own categories and keywords, so it reaches work you had no term for. - Use
search_date_rangeto separate "nothing exists" from "nothing recent".
Read enough to be sure
clio-arxiv:get_paper_details for the full record of a specific paper.
Do not characterise a paper's findings from its title. If the claim matters, get
the PDF URL with clio-arxiv:get_pdf_url, or download it with
clio-arxiv:download_paper_pdf. download_multiple_pdfs handles several
with bounded concurrency; check each result and respect service limits.
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.
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.
- 9d ago First seen · 120 lines · 45 tokens per session scan A 18938c7aa095
research-survey is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 45 tokens to every session and 1,338 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
raindrop-mcp
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
onescience-orchestrator
A task coordinator for OneScience that turns a user’s goal into a tracked plan and assigns parts of the work to suitable specialist tools.
sota-management
4-level SOTA performance tracking for VibeCodeHPC. Use when checking or updating best performance records.
authoring-gradle-builds
Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.