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 Jamie-BitFlight/claude_skills --skill graph-engineeringgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_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/jamie-bitflight/claude_skills/graph-engineering)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/graph-engineering"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/graph-engineering/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/jamie-bitflight/claude_skills/graph-engineering"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/graph-engineering.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 | $0.00062 | $0.01245 |
| Opus 5.5 | $0.00025 | $0.00498 |
| Sonnet 5.5 | $0.00012 | $0.00249 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
graph-engineering 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 28d 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
94% identical to graph-engineering — 137 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Engineering
Use graph structure only when relationships, paths, recurring identity, or execution dependencies are central to the problem. Prefer a simpler table, document index, vector search, or serial workflow when it satisfies the required questions or execution contract.
Route the request
Choose the branch that matches the user's outcome:
- Knowledge graph — model and serve durable knowledge. Follow the knowledge-graph lifecycle below and load only the reference for the current stage.
- Task graph — model work, dependencies, data flow, readiness, failure, verification, and approval. Read references/task-graphs.md.
- Learning — teach only the relevant branch. Establish the learner's goal and current understanding, use their domain when available, and alternate concept → worked example → learner application → feedback. Visualize topology when it materially improves understanding; do not force the entire lifecycle when the user asks about one part.
Knowledge-graph lifecycle
Treat competency questions as the graph's specification and end-to-end acceptance tests.
- Define value and competency questions. Write representative questions the system must answer. Stop if a simpler representation answers them adequately.
- Choose representation and fact semantics. Select property graph, RDF/OWL, or a simpler typed-edge representation. Define identity, temporal semantics, and how assertions retain evidence/provenance. Read references/modeling.md.
- Model the minimal ontology. Define only the entity, relation, event, and constraint vocabulary required by the competency questions. Validate that each question has a plausible path through the schema.
- Map or extract source data. Prefer deterministic mappings for structured data; use constrained extraction for open text. Separate entity, relation, and event extraction when doing so improves validation. Read references/extraction.md.
- Evaluate extraction. Sample representative sources and measure the error dimensions that matter to the application. Set acceptance thresholds from consequence, source variability, and downstream cost rather than a universal fixed percentage.
- Resolve identity and fuse assertions. Block candidate matches, compare identity evidence, preserve conflicting assertions and their provenance, and make merges reversible where practical. Read references/fusion-and-llm.md.
- Store, query, and operate. Choose storage and indexes from expected graph size, query shapes, update rate, consistency needs, access boundaries, and operational constraints. Define incremental ingestion, retraction/deletion, schema evolution, and integrity checks when the system persists beyond a prototype.
- Serve the graph. For GraphRAG or memory, retrieve the smallest evidence-bearing subgraph or paths that answer the query. Keep retrieval strategy configurable and evaluate it against the competency questions rather than assuming a fixed hop count. Read references/fusion-and-llm.md.
- Run end-to-end evaluation. Execute the competency questions against the resulting system. Separate extraction quality, identity/fusion quality, retrieval/query quality, answer correctness, and operational telemetry so one metric cannot hide another's failure.
What ships with it
7 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.
- 28d ago Changed 9f0e0d454b01
- 29d ago Changed · -55 lines · -90 tokens per session ec44d48e8649
- 1mo ago First seen · 124 lines · 152 tokens per session scan A 7f1c54ccf561
graph-engineering is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 1,245 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to graph-engineering, differing in 137 lines, and is treated as a copy.
Other skills, from other repositories
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.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.