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/datahub-project/datahub/agents-mdgit clone --depth 1 https://github.com/datahub-project/datahubWhat 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 | $0.07245 | $0.07245 |
| Opus 5 | $0.03623 | $0.03623 |
| Sonnet 5 | $0.01449 | $0.01449 |
| Haiku 4.5 | $0.00724 | $0.00724 |
Grade A, and why
datahub 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 3d 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 — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataHub — Agent Development Guide
This is the canonical reference for working with the DataHub codebase. It applies to all coding agents (Claude Code, Cursor, Codex CLI, Devin, etc.) and human developers alike.
Code Navigation (LSP)
Prefer LSP tools over Grep for code navigation tasks:
- Use
goToDefinitionto find where something is defined - Use
findReferencesto find all call sites - Use
workspaceSymbolto find symbols by name - Use diagnostics after any edit to catch type errors immediately
See docs/lsp-setup.md for installation and configuration.
Essential Commands
Build and test:
./gradlew build # Build entire project
./gradlew check # Run all tests (Python/JS lint lives in lint-jobs.yml / :module:lint)
./gradlew lintCheck # Run all lint checks (Python, JS, GraphQL, markdown, Java)
./gradlew lintFix # Auto-fix all lint issues
./gradlew format # Format all code (Java, Markdown, GraphQL, YAML)
# Note that each directory typically has a build.gradle file, but the available tasks follow similar conventions.
# Java code.
./gradlew spotlessApply # Java code formatting
# Python code.
./gradlew :metadata-ingestion:testQuick # Fast Python unit tests
./gradlew :metadata-ingestion:lint # Python linting (ruff, mypy)
./gradlew :metadata-ingestion:lintFix # Python linting auto-fix (ruff only)
# Markdown, GraphQL, YAML formatting
./gradlew :datahub-web-react:mdPrettierWrite # Format markdown files
./gradlew :datahub-web-react:graphqlPrettierWrite # Format GraphQL schemas
./gradlew :datahub-web-react:githubActionsPrettierWrite # Format GitHub Actions
IMPORTANT: Verifying Python code changes:
- ALWAYS use
./gradlew :metadata-ingestion:lintFixto verify Python code changes - NEVER use
python3 -m py_compile- it doesn't catch style issues or type errors - NEVER use
rufformypycommands directly - use the Gradle task instead - lintFix runs ruff formatting and fixing automatically, ensuring code quality
- For smoke-test changes, the lintFix command will also check those files
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.
- 3d ago First seen · 720 lines · 7,245 tokens per session scan A 878037f1fa6d
datahub AGENTS.md is an instructions file published in the GitHub repository datahub-project/datahub (12,629 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,245 tokens to every session, about $0.0362 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
OpenMetadata CLAUDE.md
Claude Code instructions for open-metadata/OpenMetadata, covering claude.md, about openmetadata, stack at a glance, environment setup (every session) and repository layout.
whodb AGENTS.md
AGENTS.md instructions for clidey/whodb, covering whodb development guide, git commits — hard rule, terminology, non-negotiable rules and behavioral guidelines.
OpenMetadata copilot-instructions.md
Copilot instructions for open-metadata/OpenMetadata, covering openmetadata - github copilot development instructions, core purpose, fundamental principles, 1. user-centric approach and 2. accuracy and reliability.
whodb CLAUDE.md
Claude Code instructions for clidey/whodb, a project described as: Where data access meets operational intelligence.
public-data-lens CLAUDE.md
Instructions for hike-lab/public-data-lens, covering claude.md, 구조, 설계 문서 (작업 전 확인), 책임 분리 (설계서 §2) and 불변식.
OpenMetadata AGENTS.md
AGENTS.md instructions for open-metadata/OpenMetadata, a project described as: The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.