Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add brainets/braina/plugin install brainaWrote 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/brainets/braina/hoi-metrics)<a href="https://agentmods.dev/skills/brainets/braina/hoi-metrics"><img src="https://agentmods.dev/badge/skills/brainets/braina/hoi-metrics/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/brainets/braina/hoi-metrics"><img src="https://agentmods.dev/badge/skills/brainets/braina/hoi-metrics.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 | $0.00151 | $0.01234 |
| Opus 5.5 | $0.00060 | $0.00494 |
| Sonnet 5.5 | $0.00030 | $0.00247 |
| Haiku 4.5 | $0.00015 | $0.00123 |
Grade A, and why
hoi-metrics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HOI metrics
Covers the 15 higher-order-interaction tools braina exposes. Per-metric
detail lives in references/ next to this file
(${CLAUDE_PLUGIN_ROOT}/skills/hoi-metrics/references/); read the matching
file before answering a parameter-level question.
| Tools | Reference file |
|---|---|
hoi_oinfo, hoi_gradient_oinfo, hoi_infotopo, hoi_dtc, hoi_tc, hoi_sinfo |
references/static-metrics.md |
hoi_redundancy_mmi, hoi_synergy_mmi, hoi_rsi, hoi_infotot |
references/static-metrics.md (target-y section) |
hoi_transfer_entropy, hoi_dotot, hoi_redundancy_phiid, hoi_atoms_phiid |
references/dynamic-metrics.md |
hoi_get_nbest_mult, bootstrap CIs (n_boots), samples_path, method |
references/nbest-bootstrap-estimators.md |
| CPU vs GPU, JAX memory on shared machines | references/compute-backend.md |
Input and output conventions
- Static metrics:
(n_samples, n_features)or(n_samples, n_features, n_variables); the analysis is over multiplets (all subsets of features betweenminsizeandmaxsize), not pairs. Dynamic metrics need(n_samples, n_features, n_times)and a lagtau. - Give a
.ncinput whose feature dimension has a coordinate (e.g.roi): the output then carriesmultiplet_namessuch asA / C / D. HOI itself rejects xarray, so the wrapper converts to numpy and keeps the names. - Every
hoi_*tool writes a.ncwith dims(multiplets, variables)and coordinatesmultiplets(feature indices, e.g.0,2,3),order(multiplet size) andmultiplet_names. Save as.nc;.npydrops this metadata andhoi_get_nbest_multrefuses it. - When a target
yis given to a metric that accepts it, HOI appendsyas an extra feature: multiplets containing indexn_featuresare the task-related ones and are labelled... / y. - Cost grows combinatorially with
n_featuresandmaxsize; capmaxsize(3-5) on more than ~10 features.
Sign conventions differ between metrics
What ships with it
4 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.
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.
- 29d ago Changed · -98 lines · +32 tokens per session ba1f07e4fe1c
- 1mo ago First seen · 176 lines · 119 tokens per session scan A 1285c4b4670d
hoi-metrics is a skill published in the GitHub repository brainets/braina (5 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 151 tokens to every session and 1,234 once invoked, about $0.0006 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 2026-09-14.
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.