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 bibliographygit 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/bibliography)<a href="https://agentmods.dev/skills/iowarp/clio-kit/bibliography"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/bibliography/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/bibliography"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/bibliography.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 | $0.00047 | $0.00876 |
| Opus 5.5 | $0.00019 | $0.00350 |
| Sonnet 5.5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
bibliography 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bibliography
A fabricated citation is the worst failure available here. It is fluent, correctly formatted, and points at a paper that does not exist. Every entry has to come from a tool that returned it.
Prefer clio-arxiv:export_to_bibtex for arXiv records. For other sources,
use publisher/repository citation metadata. Manual formatting or correction is
acceptable only when every field is checked against a retrieved record; never
fill gaps from memory.
Steps
1. Collect candidates.
Search by the axis that matches the question — see
research-survey for which of the seven search tools to use.
For a bibliography specifically, two are unusually useful:
clio-arxiv:search_papers_by_author— for a group's body of work, and for finding the rest of a line of research once you have one paper from it.clio-arxiv:find_similar_papers— takes a paper you already have and finds neighbours by its categories and keywords. This is how the survey stops being a keyword list and starts covering a field.
2. Verify each one you intend to cite.
clio-arxiv:get_paper_details for the full record. Check the authors, the year
and the version. A preprint's title and author list change between versions, and
citing v1's title for v3's content is a real error.
3. Export.
clio-arxiv:export_to_bibtex on the results. Read what comes back: ArXiv
metadata is author-supplied and imperfect. Names, capitalisation in titles, and
journal fields for papers since published all need checking.
4. Get the PDFs if they will be read.
clio-arxiv:get_pdf_url for a link, download_paper_pdf for one file, or
download_multiple_pdfs for several with bounded concurrency. Respect service limits and report download failures.
Preprints and published versions
An ArXiv entry is a preprint. Some are later published, often with a different title and always with a different citation. The ArXiv record does not always know this.
When it matters — a citation in a submission, or a claim resting on peer review —
check with clio-web:search for the published version and cite that. Say which
you are citing; the two are not interchangeable, and a reviewer will notice.
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 · 89 lines · 47 tokens per session scan A 4ef3cf57ea7c
bibliography is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 47 tokens to every session and 876 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-08.
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.