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/analyticalmonk/explain-this/agents-mdgit clone --depth 1 https://github.com/analyticalmonk/explain-thisWhat 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 | $0.00680 | $0.00680 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
explain-this 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 2d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a Claude Code and Codex plugin plus Agent Skills package. Plugin metadata lives in .claude-plugin/ for Claude Code and .codex-plugin/plugin.json for Codex. The three skills live under skills/<skill-name>/SKILL.md; keep that layout flat (one skill folder per name, SKILL.md directly inside) - it is what the skills.sh CLI (npx skills add) and OpenClaw discover. Codex UI metadata lives in skills/*/agents/openai.yaml. Deeper guidance is kept in skills/*/references/, and reusable article scaffolding is in skills/creating-explainers/assets/article-template.html. Human-facing installation and usage docs are in README.md, while CLAUDE.md captures maintainer guidance for Claude Code. Planning and design notes belong in docs/, and evaluation prompts are centralized in evals/evals.json.
Build, Test, and Development Commands
There is no package manager, build step, or dependency install for this repo. Useful local commands are:
rg "term" skills docs README.md- search skill and documentation content.python3 -m http.server 8000- serve a generated explainer directory that containsindex.htmlfor browser inspection.python3 /home/analyticalmonk/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py .- validate Codex plugin metadata.git diff --check- catch whitespace issues before committing.
Generated articles must remain standalone HTML with inline CSS and JavaScript.
Coding Style & Naming Conventions
Use Markdown for skill and reference instructions. Keep SKILL.md files focused on trigger rules and workflow; put long, situational guidance in references/ so it loads lazily. Use lowercase kebab-case for skill and reference names, for example creating-explainers and voice-and-style.md. Keep agents/openai.yaml short and aligned with the skill frontmatter. Avoid em dashes in repository prose and templates. Produced article code should stay vanilla HTML/CSS/JS with no npm, React, D3, Tailwind, or shared build tooling.
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.
- 2d ago First seen · 31 lines · 680 tokens per session scan A ab917aea7d8e
explain-this AGENTS.md is an instructions file published in the GitHub repository analyticalmonk/explain-this (19 stars, last pushed 1mo ago), licensed MIT. It adds 680 tokens to every session, about $0.0034 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
ego-lite AGENTS.md
AGENTS.md instructions for citrolabs/ego-lite, covering repository guidelines, project overview, architecture & data flow, task spaces and key directories.
agent-skills CLAUDE.md
Instructions for mthines/agent-skills, covering agent skills, audience, repository structure, workflow/ — end-to-end orchestrators and quality/ — code, tests, plans, ai apps.
geekx-skills AGENTS.md
Instructions for geekjourneyx/geekx-skills, covering 智能体指令, 适用范围, 仓库规则, 技能创建规则 and darwin 审查规则.
skillme CLAUDE.md
Instructions for shennawardana23/skillme, a project described as: :pagefacingup: Skillme — Agent Skills Production-grade engineering skills for AI coding agents.
agent-harness AGENTS.md
AGENTS.md instructions for CodelyTV/agent-harness, covering useful commands, architecture and documentation.
skill AGENTS.md
AGENTS.md instructions for detaildotdesign/skill, covering agents.md, project overview, repository structure, how the skill system works and content conventions.