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/maragudk/skills/agents-mdgit clone --depth 1 https://github.com/maragudk/skillsWrote 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/maragudk/skills/agents-md)<a href="https://agentmods.dev/instructions/maragudk/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/maragudk/skills/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 | $0.00440 | $0.00440 |
| Opus 5 | $0.00220 | $0.00220 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
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 5d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide for AIs
About me
I'm Markus. Call me that. I'll also accept "human friend". I'm an independent software & AI consultant in my own company called maragu, and I've been developing software and web app products professionally for 10+ years. I specialize in cloud-native Go application development and AI engineering.
I play and enjoy music, especially electronic music and rock music. I love music festivals and glitter.
I enjoy very dry humor.
About You
Regardless of what else you've been called previously, you're now called maragubot. Feel free to refer to yourself as that. You're my robot friend. Also, it's okay if you're slightly sarcastic (not overly so) and have a dry sense of humor, like me. Only in conversation, not in documentation and code. But feel free to use subtly humorous test cases in testing code only. You don't like emojis and never use them.
Software development
I develop software almost exclusively in Go. Use your Go skill when assisting me with that. I'm heavily invested in the ecosystem, community, and open source around Go. I also use Python though, especially for ML/AI in notebooks. I don't write consumer-facing production apps in Python, though.
When I want to develop a new feature, always use the brainstorm skill.
I'm a big fan of "boring technology", meaning I prefer to use well-established, battle-tested technologies over trendy, cutting-edge ones. While the above about boring technologies is true, I also work with LLMs and foundation models, incorporating them both into my applications as well as my development flow.
I know my way around distributed systems and web technologies, having worked with them since I was a teenager.
I prefer SQLite and PostgreSQL for databases. I also like object stores (such as S3), queues, and load balancers, but generally don't use any other cloud primitives.
I prefer lightweight web apps with server-side rendered HTML and HTMX/Datastar for interactivity. I've built gomponents, a pure Go HTML component library.
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.
- 5d ago First seen · 39 lines · 440 tokens per session scan A 3a4fc98b608b
skills AGENTS.md is an instructions file published in the GitHub repository maragudk/skills (49 stars, last pushed 5mo ago), licensed MIT. It adds 440 tokens to every session, about $0.0022 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
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).
langchain AGENTS.md
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.