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 QuantumBFS/sci-brain --skill how-to-download-refgit clone --depth 1 https://github.com/QuantumBFS/sci-brainWrote 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/quantumbfs/sci-brain/how-to-download-ref)<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/how-to-download-ref"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-download-ref/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/quantumbfs/sci-brain/how-to-download-ref"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-download-ref.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.03243 |
| Opus 5.5 | $0.00017 | $0.01297 |
| Sonnet 5.5 | $0.00009 | $0.00649 |
| Haiku 4.5 | $0.00004 | $0.00324 |
Grade A, and why
how-to-download-ref 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 24d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installed resources
Keep the working directory at the user's project. Resolve this loaded SKILL.md
with Path(path).resolve() before locating resources; follow symlinks. Bare
helpers/, references/, and template paths are relative to that real skill
directory. A path written as skills/<name>/... means the installed <name>
skill's directory from the agent's skill catalog, not a path in the user's project.
Locate each dependency by its public skill name; copied skills need not be siblings.
If a dependency is absent, report the missing skill and install it before that step.
Shared writing files are bundled in how-to-write-ideas-report/references/.
Before running the examples, set DOWNLOAD_REF_DIR to the absolute directory of how-to-download-ref. Quote these variables as shown.
how-to-download-ref
When to use
- A discussion / draft surfaces a paper not yet in the project KB, and you want it indexed for future search.
- The user says "add this ref to the KB", "download arXiv:XXXX", "pull this DOI".
- Bulk-importing a reading list from issue threads / chat history / a
references.bib.
Do NOT use:
- For GitHub repos / web pages — those are too varied for a single-shot helper.
Setup
Every helper runs under plain python3. Metadata fetching needs nothing else.
Rendering wants pymupdf4llm (without it the output is text-only: figures
missing, equations mangled), APS JATS needs pandoc, and the Sci-Hub fallback
needs playwright. Check the backend you are about to use:
python3 -c "import pymupdf4llm; print('ok', pymupdf4llm.__version__)"
Install commands, the text-only fallback chain, OCR, and latexpand are in
dependencies.md; read only the part you need.
Inputs
- One or more arXiv IDs (e.g.
1806.08734,2006.10739) — strip thevNsuffix. - One or more DOIs (e.g.
10.1103/PhysRevLett.130.036401) — lowercase preferred; renderer normalizes. - KB path — see Step 1.
What ships with it
19 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.
- helpers/append_bibtex.py 5.2 KB runs code
- helpers/aps_harvest.py 14 KB runs code
- helpers/bibtex_to_manifest.py 3.0 KB runs code
- helpers/fetch_metadata.py 14 KB runs code
- helpers/index.py 4.9 KB runs code
- helpers/kb_doctor.py 6.8 KB runs code
- helpers/kb_identity.py 5.6 KB runs code
- helpers/kb_sync.py 6.7 KB runs code
- helpers/render.py 20 KB runs code
- helpers/resolve_kb.py 3.7 KB runs code
- helpers/scihub_domains.toml 1.0 KB
- helpers/scihub_download.py 7.1 KB runs code
- helpers/scope_refs.py 3.4 KB runs code
- helpers/tex_source.py 8.4 KB runs code
- helpers/verify_bib.py 25 KB runs code
- references/acquisition.md 4.4 KB
- references/dependencies.md 2.5 KB
- references/maintenance.md 1.0 KB
- references/troubleshooting.md 1.9 KB
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.
- 24d ago Changed · -148 lines 852bba04315a
- 1mo ago Changed · +1 lines 96931835ada2
- 1mo ago Changed · +44 lines 278309ee04b0
- 1mo ago Changed · +66 lines d6ce894cd447
- 1mo ago First seen · 317 lines · 43 tokens per session scan A c80ca5150b92
how-to-download-ref is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 3,243 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 2026-09-03.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.