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/dmythro/agent-skills/agents-mdgit clone --depth 1 https://github.com/dmythro/agent-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/dmythro/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/dmythro/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dmythro/agent-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 | $0.01491 | $0.01491 |
| Opus 5 | $0.00745 | $0.00745 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
agent-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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI agents working in this repository.
Repository Overview
This is a documentation-only repository containing agent skills -- structured Markdown reference documents designed to be installed into AI coding agents (OpenCode, Claude Code, Copilot, etc.) via the skills.sh ecosystem. There is no application code, no build system, no dependencies, and no tests.
Structure
skills/
<skill-name>/
SKILL.md # Main entry point (has YAML frontmatter)
references/
<topic>.md # Deep-dive reference documents
allowlist.md # Tool permission patterns (optional)
Current skills: bun-api, bun-cli, git-commit, git-pr, git-ci, git-project, coderabbit.
Build / Lint / Test Commands
There are none. This repository contains only Markdown files. No package.json,
no CI/CD, no linter configuration, no test runner.
To validate changes, manually review Markdown rendering. If adding links, verify they point to valid targets.
Content Style Guidelines
SKILL.md Files (Main Entry Points)
Every skill's SKILL.md must include YAML frontmatter:
---
name: skill-name
description: >-
What the skill covers, when to use it, and when not to use it.
No trailing period. Use YAML folded scalar (>-) for multi-line
---
name: kebab-case, matches the directory namedescription: concise, plain text, no trailing period. Use YAML>-(folded scalar) for multi-line. Include trigger guidance (when to use / not use) since skills.sh uses this field for auto-loading decisions
Document Structure
- H1 heading immediately after frontmatter -- matches the skill's subject
- Opening paragraph -- bold, concise, establishes context and scope
- "When to Use" section -- bullet list of triggering scenarios
- "Critical Rule" or "Critical Rules" section -- bold, imperative, must-follow constraints
- Major topic sections (H2) covering the skill's API/CLI surface
- Key Gotchas / Best Practices -- a numbered list at the end; use either name (most skills use
## Key Gotchas) - References -- blockquote pointers to
references/*.mdfiles
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 · 172 lines · 1,491 tokens per session scan A 9f4da4793328
agent-skills AGENTS.md is an instructions file published in the GitHub repository dmythro/agent-skills (6 stars, last pushed yesterday), licensed MIT. It adds 1,491 tokens to every session, about $0.0075 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
ultimate-seo-geo AGENTS.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — llm-agnostic seo agent, 0. before you start, routing index, when not to run a full audit and audit context: internal vs. competitive.
ultimate-seo-geo GEMINI.md
Instructions for mykpono/ultimate-seo-geo, covering ultimate seo + geo — gemini cli context, instructions, key commands, install dependencies first and run all individual checks.
attractor-guided-engineering-template AGENTS.md
AGENTS.md instructions for entropy-cloud/attractor-guided-engineering-template, covering agents.md, project intent, dual-audience repo, in-tree tool and task routing.
skillkit CLAUDE.md
Instructions for sacredvoid/skillkit, covering skillkit, github pages, skill file format and git remote.
ux-ui-agent-skills CLAUDE.md
Claude Code instructions for sterlingpathological200/ux-ui-agent-skills, covering ux/ui expert agent — claude design system skill, decision framework, design principles, atomic design and design thinking.
ppt-agent CLAUDE.md
Claude Code instructions for Taffyreclaimed45/ppt-agent, covering ppt agent plugin, available commands, workflow phases, agent types and skill invocation conventions.