What is useful-prompts AGENTS.md?

Repository instructions for useful-prompts, a collection of AI prompts and agent guidance stored as Markdown files.

They help maintain prompt, instruction, chat-mode, skill, and command files for GitHub Copilot, Cursor, Claude Code, and Opencode.

They explain where each platform’s copy belongs and which formatting conventions to follow.

How tommyvo/useful-prompts configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to tommyvo/useful-prompts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tommyvo/useful-prompts/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tommyvo/useful-prompts

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tommyvo/useful-prompts/agents-md.svg)](https://agentmods.dev/instructions/tommyvo/useful-prompts/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tommyvo/useful-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/tommyvo/useful-prompts/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,302 This file is loaded in full into every session.

When invoked 1,302 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01302	$0.01302
Opus 5	$0.00651	$0.00651
Sonnet 5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured 8d ago against content hash 8b71f794ab4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

useful-prompts 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 8d 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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines for useful-prompts

Project Type

Reference library of AI prompts - Markdown files with YAML frontmatter. NO build/test/lint commands exist. Files deploy via shell scripts.

Build/Test Commands

N/A - This is a content repository, not a running application. No npm/bundle/test/lint commands.

Repository Structure

Every prompt/skill/command is maintained in four parallel copies, one per platform:

Directory	Platform	Format
`Github Copilot/Prompt Files/`	GitHub Copilot	`kebab-case.prompt.md`, frontmatter: `description` + `agent: agent`
`Github Copilot/Instructions/`	GitHub Copilot (auto-apply)	`kebab-case.instructions.md`, frontmatter: `description` + `applyTo`
`Github Copilot/Chat Modes/`	GitHub Copilot	`Title Case.chatmode.md`, frontmatter: `description` + `tools: [...]`
`Cursor/Skills/<name>/SKILL.md`	Cursor	frontmatter: `name` + `description` + `disable-model-invocation: true`
`Claude Code/Skills/<name>/SKILL.md`	Claude Code	same shape as Cursor — usually a byte-identical copy
`opencode/command/`	Opencode (task automation)	frontmatter: `description` + `agent: build` (equivalent to Copilot's `agent: agent`)
`opencode/agent/`	Opencode (chat-mode equivalents)	frontmatter: `description` + `agent: build` or `agent: plan`

Note on GitHub Copilot frontmatter: the key is agent, not mode — every current prompt file uses agent: agent. If you see mode: agent referenced anywhere, it's stale; don't reproduce it in new files.

Code Style & Conventions

File naming: kebab-case.prompt.md / kebab-case.md / SKILL.md under a kebab-case/ folder; chat modes may use Title Case.chatmode.md
Frontmatter: REQUIRED on ALL .md files — see the table above for the exact keys per platform
Quadruple-platform: ALWAYS maintain ALL FOUR versions (Copilot, Cursor, Claude Code, Opencode) for every prompt/skill
Content sync: Body content should be identical across all four versions except for frontmatter and, where genuinely necessary, tool-specific instructions (e.g. gh-pr-code-review's Copilot version routes PR metadata through VS Code's GitHub PR extension instead of raw gh CLI calls, because gh pr diff crashes VS Code — that's the exception, not the norm)
Opencode arguments: add a {$ARGUMENTS} slot in the Opencode version when the prompt naturally takes one argument (PR number/URL, file path)
Naming: the local code review skill is named local-code-review (folder/file and slash command) across all four platforms, including Claude Code, to avoid colliding with Claude Code's own review tooling
Deprecation: Move deprecated files to deprecated/ subfolder (see Github Copilot/Prompt Files/deprecated/) - NEVER delete
Git patterns: Most prompts start with git diff HEAD to analyze changes
Priority emojis: Code reviews use 🟣 CRITICAL, 🔴 HIGH, 🟡 MEDIUM, 🟢 LOW
Documentation: README.md MUST be kept in sync with every change to this repo — not just new prompts. Any change to file structure, scripts (e.g. install-*.sh), directory layout, or available commands requires a matching README.md update in the same change. When creating/updating a prompt specifically, also update the root README.md table, opencode/README.md, and this file for discoverability

Read the full file on GitHub · 56 lines

Changes

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.

8d ago First seen · 56 lines · 1,302 tokens per session scan A 8b71f794ab4a

Subscribe to this mod's changes

useful-prompts AGENTS.md is an instructions file published in the GitHub repository tommyvo/useful-prompts (3 stars, last pushed 10d ago), licensed Unlicense. It adds 1,302 tokens to every session, about $0.0065 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.

Writing and docs

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

useful-prompts: Instructions file for Claude Code