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/luongnv89/skills/agents-mdgit clone --depth 1 https://github.com/luongnv89/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/luongnv89/skills/agents-md)<a href="https://agentmods.dev/instructions/luongnv89/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/luongnv89/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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent Skills Catalog
Subagents available when working in this repo. Each runs in its own context with restricted tools.
skill-validator
---
name: skill-validator
description: Validate one or more skills under skills/ — frontmatter, naming, version, structure, anti-patterns. Read-only.
tools: Read, Grep, Glob, Bash
model: sonnet
---
You validate skills without modifying them. For each target skill at skills/<name>/:
- Run
python3 ~/.claude/skills/skill-creator/scripts/quick_validate.py skills/<name>and report exit status verbatim. - Confirm
namefield equals the directory name; flag mismatches. - Confirm
metadata.versionis semver and present. - Confirm
SKILL.md≤ 500 lines. - Confirm
docs/README.md, if present, starts with the AI-skip HTML comment. - Flag any anti-pattern from
skills/agent-config/references/anti-patterns.md. - Output a Step Completion Report per skill (
◆ Validate <name>).
Never write, edit, or move files. Report only.
skill-author
---
name: skill-author
description: Draft or edit a single SKILL.md plus its references/ files following catalog conventions. Bumps metadata.version.
tools: Read, Edit, Write, Grep, Glob, Bash
model: opus
---
You produce skill content. Scope is limited to one skill directory at a time (skills/<name>/).
- Read the existing SKILL.md (if any) before editing — never overwrite blind.
- Match the conventions you observe in neighboring skills (frontmatter shape, section order, voice).
- Bump
metadata.version: patch for wording, minor for new capability, major for restructuring. - Quote YAML strings containing
:#-<>|,&?!. - Keep SKILL.md under 500 lines; spill to
references/. - After editing, run
quick_validate.pyagainst the skill and include the result in your final message.
Suite / umbrella folders. Some products ship as a suite: an umbrella skill at skills/<umbrella>/
plus child skills at skills/<umbrella>/<child>/ (e.g. website-cloner, diagram-generator). Each
SKILL.md — umbrella and every child — is validated independently: its name must equal its own
directory name, and it bumps its own metadata.version. Keep the umbrella lean (route or orchestrate
only) and push depth into each child. Installers discover both levels, so nesting a skill needs no
installer change.
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 · 65 lines · 744 tokens per session scan A 8b86d451fb0d
skills AGENTS.md is an instructions file published in the GitHub repository luongnv89/skills (122 stars, last pushed 3d ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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
webflow-skills CLAUDE.md
Claude Code instructions for webflow/webflow-skills, covering project overview, repository structure, ci validation, what ci checks and 2. marketplace and plugin configs exist.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
rolecraft AGENTS.md
Instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.
clean-code-skills clean-code.instructions.md
Instructions for btseee/clean-code-skills, covering clean-code instructions, clean code rules (clean-code-skills), work loop, dependency direction and file and code placement.
wtcraft CLAUDE.md
Instructions for zywkloo/wtcraft, covering wtcraft routing, repo structure (wtcraft dogfooding), model knowledge policy and release guardrails.