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 dual-graph-routergit 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/dual-graph-router)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/dual-graph-router"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/dual-graph-router/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/dual-graph-router"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/dual-graph-router.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 | $0.00187 | $0.02302 |
| Opus 5 | $0.00093 | $0.01151 |
| Sonnet 5 | $0.00037 | $0.00460 |
| Haiku 4.5 | $0.00019 | $0.00230 |
Grade A, and why
dual-graph-router 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-Graph Router
Overview
The dual-graph architecture is the central framework of the book. An agentic system needs two complementary structures: a representation of what it KNOWS (the vertical knowledge graph — entities, relationships, constraints) and a representation of how it ACTS (the horizontal workflow graph — reasoning, execution, decision, and validation nodes with explicit dependencies). "The vertical graph is the map. The horizontal graph is the route."
This skill routes a request to the right structure before any work begins:
- vertical — a knowledge question answerable by one traversal. "Which
services depend on payments-db and were deployed in the last 24 hours?" is a
single
MATCHoverDEPENDS_ONedges with a temporal filter (Example 2-1), not a workflow. - horizontal — a process the agent must carry out. "Classify the alert, plan remediation, decide whether to roll back" decomposes into focused nodes.
- both — the central case from "Where the Two Graphs Meet." "Diagnose
why checkout is slow and correlate the evidence" is a horizontal workflow
whose reasoning/retrieval nodes traverse the vertical graph for the dependency
chain, then write the result back (a new
CAUSED_BYedge). The architecture's value emerges at this intersection. - unroutable — no signal for either graph; ask rather than guess (the chapter's ambiguous-situation discipline).
When to Use
- An agent receives an on-call request and must decide: lookup or process?
- You are wiring the top of a harness and need a deterministic first-hop router
- Auditing a set of historical requests to see how the workload splits across the two graphs
Phrases that should invoke this skill: "route this request", "is this a lookup or an action", "vertical or horizontal graph", "which graph handles this", "where the two graphs meet".
When NOT to Use
- Building the workflow DAG. Once a request routes to
horizontal/both, decomposition into constrained nodes isharness-node-splitter; scheduling the nodes into parallel phases isinvestigation-dag-planner(Ch5). - Choosing a graph data model. Property graph vs RDF vs hypergraph is
graph-model-selector(Ch3), a different decision. - Fixed pipelines. If the request always runs the same hardcoded steps, there is nothing to route.
- Retrieving the actual facts. This picks the STRUCTURE; it does not run the traversal or execute the workflow.
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 · 170 lines · 187 tokens per session scan A 047ca2b28790
dual-graph-router is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 187 tokens to every session and 2,302 once invoked, about $0.0009 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…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
repo_search
Search repository text through a deterministic first-class fak command.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
cortex-design
Use this skill to generate well-branded interfaces and assets for Cortex, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.