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 javded-itres/Holix --skill text-similaritygit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/javded-itres/holix/text-similarity)<a href="https://agentmods.dev/skills/javded-itres/holix/text-similarity"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/text-similarity/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/javded-itres/holix/text-similarity"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/text-similarity.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 | $0.00030 | $0.00222 |
| Opus 5.5 | $0.00012 | $0.00089 |
| Sonnet 5.5 | $0.00006 | $0.00044 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
text-similarity 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 10d 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
When to use
Call text_similarity to compare strings that are already in the conversation: a near-duplicate, or which of a few passages is closest to another.
Pass the texts in the language they are written in. Do not translate them first.
This does not search profile memory, documents, or skills, and it does not pick a label. For a closed set of answers use systemone_decide when that tool is on.
Call
- Two texts:
text_aandtext_b. Readcosine(1 is the same direction, 0 is unrelated). - Up to eight texts:
texts. Read the cosine matrix.
If the tool returns Embeddings error, say so. Do not invent a score.
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.
- 10d ago First seen · 28 lines · 30 tokens per session scan A 2f7549c5b44b
text-similarity is a skill published in the GitHub repository javded-itres/Holix (17 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 222 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 2026-10-07.
Other skills, from other repositories
rag-local-lancedb
Build, query, and manage local vector embeddings and semantic search pipelines using LanceDB and HuggingFace/SentenceTransformers embeddings without cloud dependencies.
clawrouter
Hosted-gateway LLM router — save 87% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 88 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 7 free models included. Also exposes realtime market data (global…
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.