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 agentmods add instructions/apache/hugegraph/agents-mdgit clone --depth 1 https://github.com/apache/hugegraphWhat 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 | $0.01126 | $0.01126 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
hugegraph AGENTS.md 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 yesterday.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Single source of truth for AI coding agents. README.md covers human-facing deployment/ecosystem context; only consult it on demand.
Stack & Modules
Apache HugeGraph — Apache TinkerPop 3 compliant graph database.
Java 11+, Maven 3.5+. Version managed via ${revision} (currently 1.8.0).
Client (Gremlin / Cypher / REST)
│
Server = hugegraph-server
├─ hugegraph-api REST, Gremlin/Cypher, auth
├─ hugegraph-core engine, schema, traversal, BackendStore interface
└─ Backend impls rocksdb (default, embedded) │ hstore (distributed)
▼
hugegraph-pd (placement) + hugegraph-store (Raft)
Top-level modules: hugegraph-server · hugegraph-pd · hugegraph-store ·
hugegraph-commons (shared utils & RPC) · hugegraph-struct (data types; dep of PD/Store).
Server submodules worth knowing: hugegraph-core, hugegraph-api,
hugegraph-rocksdb, hugegraph-hstore, hugegraph-test, hugegraph-dist.
Code Search Anchors
| Area | Path |
|---|---|
| Graph engine | hugegraph-server/hugegraph-core/src/main/java/org/apache/hugegraph/ |
| REST APIs | hugegraph-server/hugegraph-api/src/main/java/org/apache/hugegraph/api/ |
| Backend interface | hugegraph-server/hugegraph-core/.../backend/store/BackendStore.java |
| Auth | hugegraph-server/hugegraph-api/.../api/auth/ |
| gRPC protos | hugegraph-{pd,store}/hg-{pd,store}-grpc/src/main/proto/ |
Config roots (under each dist module's src/assembly/static/conf/):
- Server —
hugegraph.properties,rest-server.properties,gremlin-server.yaml - PD / Store —
application.yml
Build
# All modules
mvn clean install -DskipTests
# Single module
mvn clean install -pl hugegraph-server -am -DskipTests
Distributed build order (for HStore-enabled dev):
mvn install -pl hugegraph-struct -am -DskipTests # 1. shared data types
mvn clean package -pl hugegraph-pd -am -DskipTests # 2. placement driver
mvn clean package -pl hugegraph-store -am -DskipTests # 3. distributed storage
mvn clean package -pl hugegraph-server -am -DskipTests # 4. server
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.
- yesterday First seen · 109 lines · 1,126 tokens per session scan A 980c5cc47fff
hugegraph AGENTS.md is an instructions file published in the GitHub repository apache/hugegraph (3,161 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,126 tokens to every session, about $0.0056 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 2026-08-30.
Other instructions, from other repositories
tinkerpop AGENTS.md
Instructions for apache/tinkerpop, covering agents.md, primary guidance: agent skills, planning and memory: beads, canonical documentation and licensing and provenance.
code-graph AGENTS.md
Instructions for FalkorDB/code-graph, covering codegraph - agent instructions, architecture, data flow, directory structure and commands.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
pgGraph AGENTS.md
AGENTS.md instructions for Evokoa/pgGraph, covering package manager safety wrapper and pggraph source-of-truth principle.
code-graph CLAUDE.md
Instructions for FalkorDB/code-graph, a project described as: A code-graph demo using GraphRAG-SDK and FalkorDB.
cognee CLAUDE.md
Instructions for topoteretes/cognee, covering claude.md, project overview, development commands, setup and create virtual environment (recommended: uv).