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 Genefold/arrowspace-skills --skill arrowspace_skillsgit clone --depth 1 https://github.com/Genefold/arrowspace-skillsWrote 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/genefold/arrowspace-skills/arrowspace_skills)<a href="https://agentmods.dev/skills/genefold/arrowspace-skills/arrowspace_skills"><img src="https://agentmods.dev/badge/skills/genefold/arrowspace-skills/arrowspace_skills/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/genefold/arrowspace-skills/arrowspace_skills"><img src="https://agentmods.dev/badge/skills/genefold/arrowspace-skills/arrowspace_skills.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 | $0.00034 | $0.00917 |
| Opus 5 | $0.00017 | $0.00458 |
| Sonnet 5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
arrowspace 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 8d 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.
This is a copy
100% identical to arrowspace — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArrowSpace
ArrowSpace is a vector database and search library that augments nearest-neighbour search with spectral graph features. It computes a Laplacian over the item graph and uses the Rayleigh quotient to produce a $$λτ$$ (lambda-tau) score per item, enabling search that respects both semantic similarity and structural role.
When to Activate
- You need vector similarity search that goes beyond cosine / L2
- Your dataset has latent structure that proximity metrics miss
- You want to characterise the spectral properties of an embedding space
- You need graph-based retrieval with spectral awareness
Installation
pip install arrowspace
Or from source: see pyarrowspace.
Core API
Build an ArrowSpace index
from arrowspace import ArrowSpaceBuilder
import numpy as np
items = np.array([[...], [...], ...], dtype=np.float64)
params = {"eps": 1.0, "k": 6, "topk": 3, "p": 2.0, "sigma": 1.0}
aspace, gl = ArrowSpaceBuilder().build(params, items)
gl is the graph Laplacian containing the Laplacian matrix (accessed via gl.to_dense() or gl.to_csr()).
Per-item $$λτ$$ scores
After building, the ArrowSpace instance exposes spectral scores for every item:
# Indexed by item insertion order: result[i] is score for i-th item
scores = aspace.lambdas()
# Sorted ascending: list of (score, item_index) tuples
ranked = aspace.lambdas_sorted()
lambdas()— scores array aligned by item index (item 0, item 1, ...)lambdas_sorted()—(score, index)pairs sorted from least to most coherent
These are per-item spectral signatures, distinct from graph eigenvalues.
Search
query = np.array([...], dtype=np.float64)
hits = aspace.search(query, gl, tau=1.0)
# Returns list of (index, score) tuples
Parameters
| Param | Default | Description |
|---|---|---|
eps |
1.0 | Neighbourhood radius for graph construction |
k |
6 | Number of nearest neighbours |
topk |
3 | Number of top candidates to return |
p |
2.0 | Distance norm (2 = Euclidean) |
sigma |
1.0 | RBF kernel width |
What ships with it
8 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.
- 8d ago First seen · 95 lines · 34 tokens per session scan A 048b29bf2738
arrowspace is a skill published in the GitHub repository Genefold/arrowspace-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 917 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to arrowspace, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.