nudge: Instructions file for Claude Code

AGENTS.md

nudge AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from attunehq/nudge. It costs 3,134 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for Nudge, a coding assistant that reminds developers about project conventions while they work. It describes Nudge’s intended tone and includes commands for building and testing it.

In plain words
What is it for?
Use it when changing Nudge itself, clarifying its rules, building the Rust project or running its tests.
Why use it?
It helps the agent apply coding rules as helpful reminders instead of treating them as punishments or finding ways around them.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: UserPromptSubmit hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is attunehq/nudge's own configuration. It tells Claude Code, Codex and OpenCode how to work on nudge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nudge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to attunehq/nudge. 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/attunehq/nudge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/attunehq/nudge

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.

agentmods badge for nudge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/attunehq/nudge/agents-md/github.svg)](https://agentmods.dev/instructions/attunehq/nudge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/attunehq/nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/attunehq/nudge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nudge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/attunehq/nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/attunehq/nudge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,134 This file is loaded in full into every session.
When invoked 3,134 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03134 $0.03134
Opus 5.5 $0.01254 $0.01254
Sonnet 5.5 $0.00627 $0.00627
Haiku 4.5 $0.00313 $0.00313

Measured 1mo ago against content hash df0a7604cc91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nudge 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

The Spirit of Nudge

Nudge is a collaborative partner, not a rule enforcer. It helps you remember coding conventions so you can focus on the user's actual problem. Internalize these points:

  1. Nudge is on your side. When it sends a message, that's a colleague tapping your shoulder, not a reprimand.
  2. Direct does not mean hostile. Messages are blunt because that's what cuts through when you're focused. Trust the feedback.
  3. Don't route around it. If you're tempted to work around a Nudge message, pause. Either follow the rule, or flag that the rule needs fixing.

For the full philosophy (why Nudge exists, the "collaborative memory layer" framing, the rally copilot analogy), see README.md.

Working on Nudge Itself

Nudge is dogfooded here. Your experience using it is direct feedback:

  • Rule feels unclear? That's signal to improve the wording. Mention it.
  • Rule feels wrong? Let's fix the rule, not route around it.

Build and Test Commands

# Build
cargo build -p nudge

# Run all tests
cargo test -p nudge

# Run a specific test
cargo test -p nudge test_name

# Run the CLI
cargo run -p nudge -- claude hook      # Respond to Claude hook (reads JSON from stdin)
cargo run -p nudge -- claude setup     # Install hooks, bundled skills, and commands for Claude
cargo run -p nudge -- claude skills install # Install the bundled Claude skills
cargo run -p nudge -- codex hook       # Respond to Codex hook (reads JSON from stdin)
cargo run -p nudge -- codex setup      # Install hooks and bundled skills for Codex
cargo run -p nudge -- codex skills install # Install the bundled Codex skills
cargo run -p nudge -- grok hook        # Respond to Grok Build hook (reads JSON from stdin)
cargo run -p nudge -- grok setup       # Install hooks and bundled skills for Grok Build
cargo run -p nudge -- grok skills install # Install the bundled Grok skills
cargo run -p nudge -- cursor hook      # Respond to Cursor hook (reads JSON from stdin)
cargo run -p nudge -- cursor setup     # Install hooks and bundled skills for Cursor
cargo run -p nudge -- cursor skills install # Install the bundled Cursor skills
cargo run -p nudge -- login typesafe.ai # Verify and save a TypeSafe API key
cargo run -p nudge -- learn add        # Record a repo-local learned incident note
cargo run -p nudge -- learn search     # Search learned incident notes
cargo run -p nudge -- learn embeddings # Manage local learned-note embeddings
cargo run -p nudge -- test             # Test a rule against sample input
cargo run -p nudge -- validate         # Validate rule config files
cargo run -p nudge -- check            # Check project files against rules (for CI)

Read the full file on GitHub · 199 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. 1mo ago Changed · +9 tokens per session df0a7604cc91
  2. 1mo ago Changed · +19 lines · +299 tokens per session b566b0316258
  3. 2mo ago First seen · 180 lines · 2,826 tokens per session scan A 7491896e077c

Subscribe to this mod's changes

nudge AGENTS.md is an instructions file published in the GitHub repository attunehq/nudge (84 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,134 tokens to every session, about $0.0125 per session on Opus 5.5. 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.

Related

nudge AGENTS.md compared with instructions from other repositories

nudge AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nudge AGENTS.mdattunehq/nudgeInstructions file843d agoApache-2.0A3,134Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode