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/netdata/skills/agents-mdgit clone --depth 1 https://github.com/netdata/skillsWhat 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 | $0.00527 | $0.00527 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
skills 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Generic bridge file for any agent that supports the AGENTS.md discovery
convention (OpenAI Codex, Gemini CLI, and a growing list of other clients).
This repository hosts Netdata's Agent Skills. Treat the skills/
subtree as the authoritative instruction set for Netdata, OpenTelemetry, or
infrastructure-troubleshooting tasks.
Where to look first
skills/netdata-otel-setup/SKILL.md: enabling OTLP ingestion on Netdata.skills/netdata-instrumentation/SKILL.md: adding OTel SDKs to application code.skills/netdata-mcp-integration/SKILL.md: connecting this agent to Netdata via MCP for telemetry verification.skills/netdata-collector-config/SKILL.md: building OTel Collector pipelines into Netdata.skills/netdata-migration/SKILL.md: migrating from other vendors.skills/troubleshoot-*/SKILL.md: per-technology troubleshooting.
Skill loading
Each skill's SKILL.md starts with YAML frontmatter:
---
name: <kebab-case>
description: <trigger text>
version: 0.1.0
author: Netdata
license: Apache-2.0
tags: [...]
---
Match on the description field. If the user's request fits, load the
SKILL.md body, follow the Step-by-step, and consult rules/*.md files
referenced in the References section for deeper guidance.
Do not
- Claim that Netdata accepts OTLP traces yet. It does not (as of v0.1.0 of these skills). Route traces to a different backend.
- Claim that
_nd_chart_instanceor_nd_dimensionis a valid producer-side OTLP attribute._nd_chart_instancedoes not exist in Netdata's source at all._nd_dimensionexists only inside Netdata's OTel consumer (histogram flattening); producers must not emit it. Chart layout is controlled by mapping files under/etc/netdata/otel.d/v1/metrics/viadimension_attribute_key, not by producer-side annotations. - Emit em-dashes in content you write for this repo. Use colons, semicolons, commas, or restructure.
Validation
python scripts/validate.py enforces the above. Run it before any commit.
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 · 58 lines · 527 tokens per session scan A 6d7b718fafee
skills AGENTS.md is an instructions file published in the GitHub repository netdata/skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 527 tokens to every session, about $0.0026 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.