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/svngoku/coding-agents-skills/agents-mdgit clone --depth 1 https://github.com/svngoku/coding-agents-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/svngoku/coding-agents-skills/agents-md)<a href="https://agentmods.dev/instructions/svngoku/coding-agents-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/svngoku/coding-agents-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 | $0.02246 | $0.02246 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
coding-agents-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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coding-agents-skills — Agent Instructions
This document contains instructions for AI coding agents managing this repository.
Repository Overview
This is a curated collection of specialized skills for AI coding agents. Each skill lives in skills/<skill-name>/ and is designed to be loaded by agents to enhance their capabilities in specific domains (frameworks, deployment platforms, design patterns, etc.).
The repo is documentation-first: the primary artifact is Markdown. There is no build system, no tests, no dependencies. Quality is ensured through consistent structure and peer review.
Repository Structure
coding-agents-skills/
├── skills/
│ ├── <skill-name>/ # One directory per skill
│ │ ├── SKILL.md # REQUIRED — core skill definition
│ │ ├── references/ # OPTIONAL — deep-dive docs
│ │ ├── scripts/ # OPTIONAL — runnable example scripts
│ │ ├── eval.yaml # OPTIONAL — skillgrade evaluation harness
│ │ └── AGENTS.md # OPTIONAL — skill-specific agent notes
│ └── ...
├── README.md # REQUIRED — human-facing overview
├── AGENTS.md # THIS FILE
└── LICENSE # REQUIRED — MIT
Skill Conventions
Every skill MUST follow these conventions. Inconsistencies break the loading contract for agent frameworks.
1. YAML Frontmatter (REQUIRED)
Every SKILL.md MUST begin with YAML frontmatter in this exact format:
---
name: <kebab-case-skill-name>
description: >
<trigger sentence>. Use this skill whenever the user mentions <keywords>,
wants to <actions>, or works with <tools/frameworks>. Also trigger for
<related terms>.
---
Rules for description:
- Start with a trigger sentence — when/how the skill should be activated
- Mention keywords, tools, CLI commands, API names — these are how agents match
- Include "Also trigger for" with related terms users might say
- Keep it under 500 characters when possible; never exceed 1000
- Use
>folded style for multi-line descriptions
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 · 244 lines · 2,246 tokens per session scan A 3ba1ddd0af81
coding-agents-skills AGENTS.md is an instructions file published in the GitHub repository svngoku/coding-agents-skills (9 stars, last pushed 22d ago), licensed MIT. It adds 2,246 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 2026-08-31.
Other instructions, from other repositories
skill-validator CLAUDE.md
Instructions for raphaelstolt/skill-validator, covering skill-validator, project info, common commands, code conventions and architecture.
codealive-skills AGENTS.md
Instructions for CodeAlive-AI/codealive-skills, covering codealive-skills — notes for ai coding agents, what the skill is not, architecture in one sentence, releasing and writing the skill description.
pstack AGENTS.md
AGENTS.md instructions for painhardcore/pstack, covering pstack instructions for codex, direct skills, portable behavior, playbooks and repository checks.
opentikz CLAUDE.md
Claude Code instructions for opentikz/opentikz, covering opentikz — project context for claude code, what this project is, target user, explicit non-goals (do not build these) and the three-layer content model.
thai-personal-finance-planner CLAUDE.md
Claude Code instructions for satasuk03/thai-personal-finance-planner, covering claude.md, quick orientation for claude, before you start editing, where you'll be tempted to do the wrong thing and "i'll just add this section to skill.md".
codealive-skills CLAUDE.md
Instructions for CodeAlive-AI/codealive-skills, a project described as: Agent skills for CodeAlive — semantic code search and AI-powered codebase answers. Works with Claude Code, Codex, Antigravity, Cursor, OpenCode, Copilot, Windsurf, Gemini CLI, and other SKILL.md-compatible agents.