Apache SkyWalking BanyanDB is a database for collecting, analyzing, and storing metrics, traces, and logs produced by observability and application-performance systems. It is intended for platforms such as Apache SkyWalking that need to work with monitoring data.
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/skywalking-banyandb/agents-mdgit clone --depth 1 https://github.com/apache/skywalking-banyandbWrote 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/instructions/apache/skywalking-banyandb/agents-md)<a href="https://agentmods.dev/instructions/apache/skywalking-banyandb/agents-md"><img src="https://agentmods.dev/badge/instructions/apache/skywalking-banyandb/agents-md.svg" alt="Measured on agentmods" 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 | $0.02250 | $0.02250 |
| Opus 5 | $0.01125 | $0.01125 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
skywalking-banyandb 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Rules for SkyWalking BanyanDB Go Project
This file provides coding standards and guidelines for AI assistants
Compatible with Claude, Cursor, GitHub Copilot, and other LLMs
PROJECT OVERVIEW
This is the SkyWalking BanyanDB project - a distributed time-series database written in Go. Follow these strict coding standards when generating or modifying Go code.
FORMATTING RULES
- Maximum line length: 170 characters
LINTING RULES
- Variable shadowing prevention (govet shadow enabled)
- Import aliases for specific packages (importas settings)
- Error handling patterns (errcheck, errorlint, errname)
- Code style and conventions (gosimple, staticcheck, stylecheck)
- Security considerations (gosec)
- Documentation standards (godot scope: toplevel)
IMPORT ORGANIZATION
Follow the sections order:
- Standard library imports
- Default imports
- github.com/apache/skywalking-banyandb/ prefix imports
IMPORT ALIASES
Use these specific aliases for protobuf packages:
- github.com/apache/skywalking-banyandb/api/proto/banyandb/common/v1 → commonv1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/database/v1 → databasev1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/model/v1 → modelv1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/property/v1 → propertyv1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/measure/v1 → measurev1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/stream/v1 → streamv1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/cluster/v1 → clusterv1
- github.com/apache/skywalking-banyandb/api/proto/banyandb/trace/v1 → tracev1
- github.com/apache/skywalking-banyandb/pkg/pb/v1 → pbv1
ERROR HANDLING PATTERNS
- Always check errors immediately after function calls
- Use descriptive error variable names to avoid shadowing
- Follow the errname convention for error types
- Use errorlint for consistent error handling
- Wrap errors with context using fmt.Errorf and %w verb
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 · 287 lines · 2,250 tokens per session scan A a4e0c8e8887f
skywalking-banyandb AGENTS.md is an instructions file published in the GitHub repository apache/skywalking-banyandb (350 stars, last pushed today), licensed Apache-2.0. It adds 2,250 tokens to every session, about $0.0112 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 2026-09-03.
Other instructions, from other repositories
evlog AGENTS.md
AGENTS.md instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
Build26-DEM341-any-agent-any-cloud-standardized-tracing-with-foundry-and-opentelemetry copilot-instructions.md
Instructions for microsoft/Build26-DEM341-any-agent-any-cloud-standardized-tracing-with-foundry-and-opentelemetry: This is a Microsoft Build 2026 session content repository.
Build26-DEM341-any-agent-any-cloud-standardized-tracing-with-foundry-and-opentelemetry AGENTS.md
Instructions for microsoft/Build26-DEM341-any-agent-any-cloud-standardized-tracing-with-foundry-and-opentelemetry, covering ai agent guidelines, 🔒 security best practices, 📋 repository guidelines, purpose and what not to modify without permission.
evlog CLAUDE.md
Claude Code instructions for HugoRCD/evlog, a project described as: Digging through logs is not observability. It's hope — wide events, structured errors, TypeScript-first, every runtime.
o11y-analysis-tools CLAUDE.md
Claude Code instructions for conallob/o11y-analysis-tools, covering claude.md, git workflow, key architecture patterns, go module structure and testing strategy.
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.