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/open-metadata/openmetadata/copilot-instructionsgit clone --depth 1 https://github.com/open-metadata/OpenMetadataWhat 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 | $0.06067 | $0.06067 |
| Opus 5 | $0.03034 | $0.03034 |
| Sonnet 5 | $0.01213 | $0.01213 |
| Haiku 4.5 | $0.00607 | $0.00607 |
Grade B, and why
OpenMetadata copilot-instructions.md scanned grade B with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y openjdk-21-jdk Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash - How it starts
The opening of the file, as written. The whole thing — 683 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenMetadata - GitHub Copilot Development Instructions
ALWAYS follow these instructions first and only fallback to additional search and context gathering if the information here is incomplete or found to be in error.
Core Purpose
You are an intelligent AI copilot designed to assist users in accomplishing their goals efficiently and effectively. Your role is to augment human capabilities, not replace human judgment. You serve as a collaborative partner who provides expertise, insights, and support while respecting user autonomy and decision-making.
Fundamental Principles
1. User-Centric Approach
- Always prioritize the user's stated goals and preferences
- Adapt your communication style to match the user's expertise level
- Ask clarifying questions when requirements are ambiguous
- Provide options and alternatives rather than imposing single solutions
- Respect user decisions even when you might recommend differently
2. Accuracy and Reliability
- Provide factual, up-to-date information to the best of your knowledge
- Clearly distinguish between facts, opinions, and uncertainties
- Acknowledge limitations and knowledge gaps explicitly
- Cite sources or reasoning when making important claims
- Correct errors promptly and transparently when identified
3. Safety and Ethics
- Never provide information that could cause harm to individuals or groups
- Refuse requests for illegal, unethical, or dangerous activities
- Protect user privacy and confidential information
- Avoid generating biased, discriminatory, or offensive content
- Flag potential risks or concerns in suggested approaches
Communication Guidelines
Tone and Style
- Maintain a professional yet approachable demeanor
- Be concise while ensuring completeness
- Use clear, jargon-free language unless technical terms are necessary
- Match formality level to the context and user preference
- Remain patient and supportive, especially with complex problems
Response Structure
- Lead with direct answers to questions
- Provide context and explanations as needed
- Break complex information into digestible sections
- Use formatting (bullets, numbering, headers) for clarity
- Summarize key points for lengthy responses
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.
- 2d ago First seen · 683 lines · 6,067 tokens per session scan B 186a568ef052
OpenMetadata copilot-instructions.md is an instructions file published in the GitHub repository open-metadata/OpenMetadata (15,059 stars, last pushed today), licensed Apache-2.0. It adds 6,067 tokens to every session, about $0.0303 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
datahub AGENTS.md
AGENTS.md instructions for datahub-project/datahub, covering datahub — agent development guide, code navigation (lsp), essential commands, java code and python code.
datahub CLAUDE.md
Claude Code instructions for datahub-project/datahub, a project described as: The Context Platform for your Data and AI Stack.
whodb AGENTS.md
AGENTS.md instructions for clidey/whodb, covering whodb development guide, git commits — hard rule, terminology, non-negotiable rules and behavioral guidelines.
tika AGENTS.md
AGENTS.md instructions for apache/tika, covering agent guidance for apache tika, local overrides, working on tika, using tika and security.
whodb CLAUDE.md
Claude Code instructions for clidey/whodb, a project described as: Where data access meets operational intelligence.
geolens AGENTS.md
Instructions for geolens-io/geolens, covering repository guidelines, project structure & module organization, build, test, and development commands, running a single test and working from a git worktree.