agentmods.dev

attention-please AGENTS.md

Repository instructions for the attention-please project, a Bash script that speaks a project name and plays a sound while working in a Git repository.

In plain words
What is it for?
Use them when modifying the script, its documentation, or tests, including checking Bash syntax and configuring the spoken name or sound.
Why use it?
They give contributors the expected file layout, commands, naming rules, and testing checks so changes remain consistent with the project.

Instructions file for CodexOpenCode

5 4mo ago A scan 515 tokens original MIT
View the source file Mindgames/attention-please
Install

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.

agentmods
npx agentmods add instructions/mindgames/attention-please/agents-md
Clone the repo
git clone --depth 1 https://github.com/Mindgames/attention-please

Made for: Codex, OpenCode.

Per session 515 This file is loaded in full into every session.
When invoked 515 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00515 $0.00515
Opus 5 $0.00258 $0.00258
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash ba95c83cf814, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

attention-please 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • scripts/attention-please.sh is the main executable and contains all bash logic.
  • SKILL.md defines the Codex skill metadata and expected behavior.
  • README.md documents install and usage; keep it aligned with script behavior.
  • LICENSE and .gitignore live at the repo root.
  • If tests are added, place them under tests/ to keep the root tidy.

Build, Test, and Development Commands

This repo has no build step. Run the script directly:

  • scripts/attention-please.sh — run inside a git repo to infer the project name.
  • ATTENTION_PLEASE_PROJECT="quiz-juice" scripts/attention-please.sh — override the spoken name.
  • ATTENTION_PLEASE_SOUND="/System/Library/Sounds/Ping.aiff" scripts/attention-please.sh — override the sound file.
  • bash -n scripts/attention-please.sh — quick bash syntax check.

Coding Style & Naming Conventions

  • Bash only; keep #!/usr/bin/env bash and set -euo pipefail.
  • Indent with 2 spaces in conditional blocks.
  • Environment variables are uppercase with underscores (e.g., ATTENTION_PLEASE_PROJECT).
  • Script files use kebab-case names with a .sh suffix.

Testing Guidelines

  • There is no automated test suite yet.
  • Manual verification: run scripts/attention-please.sh inside a repo and confirm sound, speech, and fallback behavior.
  • If you add tests, document the framework and keep fixtures under tests/.

Configuration & Environment

  • macOS is required for afplay and say; the script prints a message if say is missing.
  • Run from a git repo so git remote get-url origin can resolve a project name, or set ATTENTION_PLEASE_PROJECT.
  • Avoid adding network or destructive operations; this script should remain side-effect light.

Agent Behavior

  • Use the attention-please script to play the alert at the end of each turn or whenever user input/confirmation is needed.

Commit & Pull Request Guidelines

  • Use short, imperative commit messages; current history shows Initial attention-please skill.
  • Keep changes scoped; update README.md and SKILL.md when behavior changes.
  • PRs should include a brief description, manual verification steps, and any OS-specific notes.

Read the full file on GitHub · 40 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.

  1. 2d ago First seen · 40 lines · 515 tokens per session scan A ba95c83cf814

Subscribe to this mod's changes

attention-please AGENTS.md is an instructions file published in the GitHub repository Mindgames/attention-please (5 stars, last pushed 4mo ago), licensed MIT. It adds 515 tokens to every session, about $0.0026 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.

Git and workflowTestingWriting and docsclaude-codecodex-cliskills
Related

Other instructions, from other repositories

agent-orchestrator AGENTS.md

AGENTS.md instructions for Untrivial-ai/agent-orchestrator, covering agents.md, repo layout, commands, where to look first and distribution.

Untrivial-ai/agent-orchestrator · 2,282 tokens

agent-orchestrator CLAUDE.md

Claude Code instructions for Untrivial-ai/agent-orchestrator, covering claude.md, app state lives under /.ao only and design system.

Untrivial-ai/agent-orchestrator · 486 tokens

neo-skills AGENTS.md

Instructions for Benknightdark/neo-skills, covering neo-skills agents.md, 1. project overview, 2. commands, 3. workflow and 4. forbidden antipattern redlines.

Benknightdark/neo-skills · 777 tokens

skrills AGENTS.md

Instructions for athola/skrills, covering ai agent development guidelines, guiding principles, development workflow, implementation cycle and when stuck.

athola/skrills · 2,395 tokens

llm-engineering-skills CLAUDE.md

Instructions for itsmostafa/llm-engineering-skills, covering claude.md, repository purpose, repository files, skill structure and skill.md requirements.

itsmostafa/llm-engineering-skills · 524 tokens

codex-pr-review-toolkit-minimal AGENTS.md

AGENTS.md instructions for kyto64/codex-pr-review-toolkit-minimal, covering instructions, repository, layout, internationalization and subagents (issue #14).

kyto64/codex-pr-review-toolkit-minimal · 754 tokens