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/alexwoo-awso/skeleton/agents-mdgit clone --depth 1 https://github.com/alexwoo-awso/skeletonWrote 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/alexwoo-awso/skeleton/agents-md)<a href="https://agentmods.dev/instructions/alexwoo-awso/skeleton/agents-md"><img src="https://agentmods.dev/badge/instructions/alexwoo-awso/skeleton/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 5.1 | $0.01031 | $0.01031 |
| Opus 5 | $0.00515 | $0.00515 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade C, and why
skeleton AGENTS.md scanned grade C with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Describe your system architecture. Examples: --> Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Best approach:** Use cross-platform code that doesn't need output suppression (e.g., `subprocess.DEVNULL` in Python, `stdio: 'ignore'` in Node.js). Copies of this mod
1 near-identical copy found in the catalogue:
- skeleton CLAUDE.md — 88% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents working with code in this repository. It follows the AGENTS.md open standard supported by Codex CLI, OpenClaw, Cursor, Aider, Google Jules, Gemini CLI, Windsurf, Devin, and many other tools.
Claude Code users: See
CLAUDE.mdfor Claude Code specific instructions. Codex CLI users: See.codex/config.tomlfor project-level Codex configuration.
Project Overview
Project Name - Brief description of what the project does.
Architecture
Key Integration Points
Development Commands
Setup
# Initial setup steps
Development
# How to run the project locally
Testing
# How to run tests
Code Quality
# Linting, formatting, type checking commands
Architecture Deep Dive
Database Layer
Configuration System
Authentication
Critical Development Rules
These rules prevent recurring bugs documented in TODO.md and LESSONS_LEARNED.md:
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 · 171 lines · 1,031 tokens per session scan C 8cfcca1fe8cc
skeleton AGENTS.md is an instructions file published in the GitHub repository alexwoo-awso/skeleton (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,031 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
claude-skills-library AGENTS.md
AGENTS.md instructions for frankxai/claude-skills-library, covering repository instructions, classification, agent rules, class-specific guidance and handoff.
claude-project-scaffolding CLAUDE.md
Instructions for madison-hutson/claude-project-scaffolding, covering claude.md, stop — read this first, first session?, the 13 rules and context management.
Djordjes-Claude-Setup CLAUDE.md
Claude Code instructions for DjordjeMojsilovic/Djordjes-Claude-Setup, a project described as: My personal Claude setup – 11 custom skills, CLAUDE.md config and a complete prompting guide for vibe coding and multi-agent workflows.
ai-studio CLAUDE.md
Instructions for Lucas-Ren/ai-studio, a project described as: 用 AI 辅助制作短视频的完整系统，支持 Claude Code 和 Codex.
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 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).