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 rag-mcp-tool-selectiongit 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/rag-mcp-tool-selection)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/rag-mcp-tool-selection"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/rag-mcp-tool-selection/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/rag-mcp-tool-selection"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/rag-mcp-tool-selection.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 | $0.00132 | $0.02354 |
| Opus 5 | $0.00066 | $0.01177 |
| Sonnet 5 | $0.00026 | $0.00471 |
| Haiku 4.5 | $0.00013 | $0.00235 |
Grade A, and why
rag-mcp-tool-selection 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAG-MCP Tool Selection
Overview
The Model Context Protocol's tools/list operation returns every tool an agent
has access to. At enterprise scale this consumes the context window before the
agent has done any reasoning. The book's worked anchor is Block's Goose agent —
12,000 employees, 60+ MCP servers — where employees enabled every server
"just in case" and tool descriptions ate the entire prompt budget.
The chapter cites measurable degradation from the RAG-MCP research:
| Tools available | Selection accuracy (baseline LLM) |
|---|---|
| 10 | Near-perfect |
| 100 | Begins to degrade |
| 1,000 | Below 40% |
RAG-MCP replaces tools/list with a semantic search over tool metadata.
Reported benchmarks: 50-70% prompt-token reduction, selection accuracy
13.62% → 43.13%, response time -60%. This skill is the smallest unit of
that pattern — a function you can run before any LLM call to filter the
tools you actually inject.
When to Use
Trigger contexts:
- Building an MCP-based agent with 30+ tools exposed
- A user asks the agent something that could match many tools, you want top-K
- Migrating an existing single-shot prompt to MCP and the prompt is too big
- Authoring a new tool registry — you want to verify each tool is findable
Phrases that should invoke this skill: "filter the tools", "which tools should the agent use", "the prompt is too big", "RAG-MCP", "tool selection", "reduce prompt bloat".
When NOT to Use
- Under 10 tools. The book is explicit: with 10 tools the model achieves near-perfect selection. Filtering buys you nothing and adds latency.
- Fixed-pipeline scripts where the tool sequence is hardcoded — no retrieval needed.
- As a replacement for an MCP server. This skill picks WHICH tools an MCP server should expose for a query; it does not replace the server.
- As a quality gate. Use the SkillNet five-dimension framework (Ch6) for skill-quality evaluation, not this skill.
- For multi-tool workflow planning. This returns top-K tools by query similarity, not a dependency graph of tools. For collaborative-tool retrieval, see Baidu's COLT (Ch6) — out of scope here.
What ships with it
3 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.
- 11d ago First seen · 174 lines · 132 tokens per session scan A c7a93ddd9a0d
rag-mcp-tool-selection is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 2,354 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…