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 agentmods add skills/nanoagentteam/research-claw/user-previewnpx skills add nanoAgentTeam/research-claw --skill user-previewgit clone --depth 1 https://github.com/nanoAgentTeam/research-clawWrote 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/nanoagentteam/research-claw/user-preview)<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/user-preview"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/user-preview.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00300 |
| Opus 5 | $0.00021 | $0.00150 |
| Sonnet 5 | $0.00008 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
user-preview 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 5d 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.
What it actually says
User Preview: Compile & Deliver PDF
Compile the project and deliver the PDF to the user in chat.
SOP
-
Compile — Call
latex_compilewithmain_fileset to the project's main .tex file path (e.g.main.texorsubdir/main.tex). Useread_fileto locate it first if unsure.- If compilation fails, report the errors to the user and stop.
-
Send PDF — Extract the PDF filename from the
latex_compileresult and callsend_fileto deliver it.- Use a brief caption summarizing the result (e.g. success, warning count).
-
Report — Inform the user the PDF has been sent. Mention warning count if any.
- If the user requests changes, make edits and re-run this flow.
Notes
- The PDF path is relative to the project core directory, typically
main.pdf. - If
latex_compilereports warnings, mention the count in the caption — no need to list each one. - Never attempt to send a PDF without compiling first.
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.
- 5d ago First seen · 33 lines · 42 tokens per session scan A 6d27a0f8352e
user-preview is a skill published in the GitHub repository nanoAgentTeam/research-claw (292 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 300 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.
Other skills, from other repositories
latex-rescue
Diagnose and fix LaTeX compilation errors. Handles undefined control sequences, missing brackets, math mode violations, package conflicts, undefined references, and environment mismatches.
pdf2tex
Convert PDF documents back into editable LaTeX source code. Extracts text, math, tables, figures, and structure. Uses pymupdf + AI for intelligent reconstruction.
xberg
Extract text, tables, metadata, and images from 97+ document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg CLI.
latex-engine
Activate when the user wants to export a completed paper draft to production-ready LaTeX (.tex) and PDF. Converts draft.md + references.bib + figures/ into a complete arxiv-style LaTeX project with properly resolved \citep/\citet citations, booktabs tables, figure environments, and compiled PDF output.
sci-hub-download
通过 DOI 下载论文 PDF，三路线组合（OA直链 → Sci-Hub镜像 → 出版商直连）。触发词：/sci-hub、下载论文、sci-hub下载、DOI下载.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.