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 h4vzz/awesome-ai-agent-skills --skill context-rankinggit clone --depth 1 https://github.com/h4vzz/awesome-ai-agent-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/h4vzz/awesome-ai-agent-skills/context-ranking)<a href="https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/context-ranking"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/context-ranking/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/h4vzz/awesome-ai-agent-skills/context-ranking"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/context-ranking.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 | $0.00031 | $0.02807 |
| Opus 5 | $0.00015 | $0.01404 |
| Sonnet 5 | $0.00006 | $0.00561 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
context-ranking 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 11d 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
92% identical to context-ranking — 2 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Ranking
Context ranking is the process of ordering retrieved text chunks so the most relevant, diverse, and useful information rises to the top. In any retrieval pipeline, the initial search returns a broad set of candidates -- many of which are only tangentially related to the query. Ranking transforms this unordered candidate set into a prioritized list, enabling downstream steps (context assembly, prompt construction) to select the best material and discard the rest. Effective ranking is the difference between a grounded, precise answer and a vague, off-topic one.
Workflow
-
Collect Candidate Chunks: Gather the initial set of retrieved chunks from the search layer. This is typically the top-k results (k = 15-30) from a vector search, keyword search, or hybrid search. Each chunk arrives with a preliminary score (e.g., cosine similarity or BM25 score) and source metadata.
-
Apply First-Stage Scoring: Score each candidate with a fast, lightweight algorithm. BM25 is the standard choice for keyword relevance; cosine similarity between the query embedding and chunk embedding is the standard for semantic relevance. In hybrid pipelines, compute both scores and combine them using Reciprocal Rank Fusion (RRF) or a weighted linear combination. This stage is meant to be fast and run over all candidates.
-
Rerank with a Cross-Encoder: Pass the top candidates (typically 15-25) from the first stage through a cross-encoder reranker. Unlike bi-encoder embeddings that score query and document independently, a cross-encoder processes the query and chunk together with full attention, producing much more accurate relevance scores. Models like Cohere Rerank,
bge-reranker-v2-m3, or ColBERTv2 are commonly used. This step is slower but dramatically improves precision. -
Apply Diversity Selection: After reranking, the top results may cluster around a single subtopic, leaving other aspects of the query uncovered. Apply Maximal Marginal Relevance (MMR) or a similar diversity algorithm to penalize chunks that are too similar to already-selected chunks. This ensures the final ranked list covers the breadth of the query, not just its most obvious interpretation.
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.
- 11d ago First seen · 120 lines · 31 tokens per session scan A c58bf1430356
context-ranking is a skill published in the GitHub repository h4vzz/awesome-ai-agent-skills (34 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 2,807 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to context-ranking, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
llamaindex
Skill "llamaindex" from ashish7802/awesome-api-skills, covering llamaindex skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
pinecone
Pinecone stores vector embeddings for fast similarity search, serving as the memory layer for RAG (Retrieval-Augmented Generation) applications.
cohere
Cohere provides industry-leading semantic search embeddings (Embed v3), document reranking (Rerank v3), and conversational reasoning with citations (Command R+).
qdrant
Qdrant is a production-grade vector similarity search engine with extended payload-based filtering, hybrid search (dense + sparse vectors), and multi-tenant collection partitioning.
mistral
Mistral AI provides frontier open and commercial AI models, featuring mistral-large-latest, mistral-small-latest, codestral-latest for coding, and mistral-embed for semantic search.
weaviate
Weaviate is an open-source AI vector search engine designed for scalable semantic search, multi-modal embeddings, and Retrieval-Augmented Generation (RAG).