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 AnthonyAlcaraz/agentic-graph-rag-skills --skill rrf-hybrid-retrievalgit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-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/anthonyalcaraz/agentic-graph-rag-skills/rrf-hybrid-retrieval)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/rrf-hybrid-retrieval"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/rrf-hybrid-retrieval/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/anthonyalcaraz/agentic-graph-rag-skills/rrf-hybrid-retrieval"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/rrf-hybrid-retrieval.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 | $0.00144 | $0.01742 |
| Opus 5 | $0.00072 | $0.00871 |
| Sonnet 5 | $0.00029 | $0.00348 |
| Haiku 4.5 | $0.00014 | $0.00174 |
Grade A, and why
rrf-hybrid-retrieval 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 12d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RRF Hybrid Retrieval
Overview
A DevOps incident query like "latency spike in checkout related to recent deploy" needs four kinds of retrieval:
- Semantic: conceptually similar past incidents (vector similarity)
- Keyword: exact identifiers (
checkout-api,deploy-v3.5.0) - Graph traversal: connected entities (services that depend on checkout-api; deploys that touched it)
- Temporal: recent events (last 24h, by deploy timestamp)
Any single channel misses; semantic loses exact identifiers, keyword misses synonyms, graph misses isolated nodes, temporal misses the "happened before 24h ago but matters" cases. The fusion is the point.
Reciprocal Rank Fusion (Cormack et al. 2009):
RRF(item) = sum over channels c of: 1 / (k + rank_c(item))
Where k=60 is the standard. Rank-based — no score calibration needed.
Items missing from a channel contribute zero from that channel. Items
ranked high across multiple channels naturally rise to the top.
After fusion, run a cross-encoder reranker over the top-N for precision, then apply a token-budget filter so the result fits the downstream LLM's context window. Per HINDSIGHT (Latimer et al. 2025, cited in Ch4): "After RRF, a neural cross-encoder reranker refines precision on top candidates, then token budget filtering ensures results fit the downstream LLM's context window."
When to Use
- Memory queries that span multiple retrieval-channel "shapes" (conceptual
- exact + connected + recent)
- Production DevOps incident-investigation, customer-support resolution, research-synthesis agents
- When you need to combine heterogeneous retrieval methods and don't want to calibrate scores across them
Phrases: "hybrid retrieval", "RRF", "reciprocal rank fusion", "multi- channel search", "combine semantic and keyword", "cross-encoder rerank".
When NOT to Use
- Single-channel retrieval is sufficient (e.g. keyword-only ID lookup)
- One channel dominates and the others contribute noise
- Real-time hot path where the cross-encoder rerank exceeds latency budget (~50-200ms typical) — fall back to RRF without rerank
What ships with it
2 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.
- 12d ago First seen · 135 lines · 144 tokens per session scan A e87ee3ec0c7b
rrf-hybrid-retrieval is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 144 tokens to every session and 1,742 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
library
Sync agent memory files to a Cortex knowledge graph for enhanced retrieval, hybrid search (vector + keyword + graph), AI-powered Q&A with agentic deep research, and knowledge graph exploration.
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
jetson-inference-mem-tune
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
neuron-test-engineer
Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…