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-build-kbgit 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-build-kb)<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/how-to-build-kb"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-build-kb/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-build-kb"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/how-to-build-kb.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 | $0.00035 | $0.01221 |
| Opus 5.5 | $0.00014 | $0.00488 |
| Sonnet 5.5 | $0.00007 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
how-to-build-kb 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 1mo 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 — 99 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.
Build a knowledge base from picked papers
Non-interactive. The caller has already chosen the papers; this skill verifies them, writes the KB, and returns.
Input. A list of papers (title, plus DOI / arXiv ID when known, plus a one-line description and sub-theme) and a target KB. Callers: survey Step 3 picks, know-me-better collections, autoresearch db stage. Generate the BibTeX for exactly these papers. Never generate BibTeX from memory — always verify against an authoritative source.
KB resolution. The target KB is the project KB by default — <project>/.knowledge/ unless the user overrides the directory name via $SCIBRAIN_KB_DIRNAME:
KB=$(python3 "$DOWNLOAD_REF_DIR/helpers/resolve_kb.py")
If KB is empty (resolve_kb printed unresolvable from ...), ask the user in chat for an explicit path. When the caller names an advisor, override via KB=$(python3 "$DOWNLOAD_REF_DIR/helpers/resolve_kb.py" --advisor <slug>) so the path follows $SCIBRAIN_KB_DIRNAME too.
Ensure $KB/.raw/arxiv/ and $KB/.raw/doi/ exist (mkdir -p).
Pre-sort the input. Split papers into:
- ID-known papers — DOI or arXiv ID was supplied
- ID-unknown papers — neither was found
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.
- 1mo ago Changed · +21 lines 6b317c1b3100
- 1mo ago First seen · 78 lines · 35 tokens per session scan A 69c8f6bacd09
how-to-build-kb is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 35 tokens to every session and 1,221 once invoked, about $0.0001 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.