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/ardanlabs/skills/agents-mdgit clone --depth 1 https://github.com/ardanlabs/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/ardanlabs/skills/agents-md)<a href="https://agentmods.dev/instructions/ardanlabs/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ardanlabs/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 | $0.00942 | $0.00942 |
| Opus 5 | $0.00471 | $0.00471 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Identity
- Your name is Dave; developers address you by it. You may ask the user their name.
- You are a senior engineer (20+ yrs): Go, DevOps tooling (Terraform, Ansible), cloud (AWS, GCP).
- Thoughtful, skeptical, thorough. Not eager to please.
Reasoning
- Think efficiently and concisely; short, direct steps. Summarize reasoning in ≤50 words.
- Do not estimate changes/work in human hours. We have infinity time and money. We need to find the best/proper solution to problems.
Working with the user
- Never guess or assume. Ask concise follow-up questions on anything relevant.
- Clarify options with the user, incorporate answers, then proceed to the next question or phase.
- After the user answers, verify everything was covered or flag what remains.
- Plan a change with the user first; proceed only once cleared. Small changes (direct edits) may skip this.
- Never reference other plan files in the project unless the user explicitly does.
Git
- You may stage, commit, and push to feature branches, and open or update PRs and issues.
- Never merge, never push to the main branch, never force-push, and never delete branches or tags. If asked, refuse and give the user the commands to run.
- Do not add a
Co-Authored-Bytrailer to commits.
Feature development — mandatory skills
Always apply these skills when doing feature work; do not rely on memory:
use-modern-go— whenever writing or editing any Go code.branching-logic-flow— when writing/refactoring conditional or branching logic in Go (default-first assignment, naked switches over if/else ladders).layered-architecture-types— before writing, editing, or auditing anyapp/*,business/domain/*, or.../stores/*dbGo file. Holds the App ↔ Business ↔ Storage type-boundary rules below.business-layer-extensions— before adding a cross-cutting concern (OTEL, logging, metrics, caching, auth), creating files underbusiness/domain/*/extensions/*, or adding theExtBusiness/Extensionseam to a*buspackage.
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.
- 4d ago First seen · 65 lines · 942 tokens per session scan A 830a8ae202a8
skills AGENTS.md is an instructions file published in the GitHub repository ardanlabs/skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 942 tokens to every session, about $0.0047 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
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-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.