hugegraph-ai AGENTS.md

Repository instructions for HugeGraph AI, a Python workspace containing modules that connect AI tools with the HugeGraph graph database. They describe the modules, code-search guidance, build commands, and testing expectations.

In plain words
What is it for?
Use them when working on HugeGraph AI modules, especially the frequently changed hugegraph-llm module, shared dependencies, builds, or tests.
Why use it?
They help an agent understand which module owns a change and what tests are expected. This reduces accidental edits across unrelated parts of the workspace.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/apache/hugegraph-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/apache/hugegraph-ai

Made for: Codex, OpenCode.

Per session 648 This file is loaded in full into every session.
When invoked 648 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00648 $0.00648
Opus 5 $0.00324 $0.00324
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured yesterday against content hash b449241bef2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hugegraph-ai 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.

AGENTS.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working in this repository. Keep README content in README files; keep this file focused on decisions agents commonly get wrong.

Stack & Modules

  • This is a Python uv workspace. Prefer root-level workspace commands unless a module-specific file says otherwise.
  • hugegraph-llm/ is the primary and most frequently changed module. When editing or reviewing it, read hugegraph-llm/AGENTS.md first.
  • hugegraph-python-client/ is a supporting dependency for HugeGraph access. Change it only when the client contract itself must change, and verify hugegraph-llm callers when you do.
  • Treat hugegraph-ml/ and vermeer-python-client/ as lower-frequency modules. Do not expand changes into them without a direct reason.

Testing Expectations

  • Any code change must include sufficient and effective test coverage for the changed behavior, regression risk, or failure path.
  • Do not add tests that only improve coverage numbers while mocking away the behavior being changed.
  • If a change cannot reasonably include automated tests, state why and provide the manual verification performed.
  • Cross-module or shared dependency changes must test the affected downstream module, not only the package where the edit was made.

Code Search Anchors

  • hugegraph-llm/src/hugegraph_llm/ - main LLM, RAG, KG, prompt, API, and vector-index code.
  • hugegraph-python-client/src/pyhugegraph/ - Python client used by LLM code to talk to HugeGraph.
  • pyproject.toml and module pyproject.toml files - workspace membership, dependency groups, lint settings, Python versions.
  • rules/README.md - staged AI-assisted workflow for multi-file features, API contract changes, or cross-module design changes.

Build & Test

uv sync --all-extras
uv run ruff format --check .
uv run ruff check .
  • Run tests for the affected module rather than defaulting to a full-repository test sweep.
  • For hugegraph-llm, use the module CI split between unit-style tests and integration tests.
  • For hugegraph-python-client, include client tests and any hugegraph-llm tests needed to validate caller compatibility.

Read the full file on GitHub · 49 lines

Changes

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.

  1. yesterday First seen · 49 lines · 648 tokens per session scan A b449241bef2b

Subscribe to this mod's changes

hugegraph-ai AGENTS.md is an instructions file published in the GitHub repository apache/hugegraph-ai (141 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 648 tokens to every session, about $0.0032 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.