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/attunehq/nudge/agents-mdgit clone --depth 1 https://github.com/attunehq/nudgeWhat 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 | $0.02826 | $0.02826 |
| Opus 5 | $0.01413 | $0.01413 |
| Sonnet 5 | $0.00565 | $0.00565 |
| Haiku 4.5 | $0.00283 | $0.00283 |
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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- nudge CLAUDE.md — 97% identical, 20 lines differ
How it starts
The opening of the file, as written. The whole thing — 180 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:
- Nudge is on your side. When it sends a message, that's a colleague tapping your shoulder, not a reprimand.
- Direct does not mean hostile. Messages are blunt because that's what cuts through when you're focused. Trust the feedback.
- 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 -- 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)
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.
- 3d ago First seen · 180 lines · 2,826 tokens per session scan A 7491896e077c
nudge AGENTS.md is an instructions file published in the GitHub repository attunehq/nudge (82 stars, last pushed 17d ago), licensed Apache-2.0. It adds 2,826 tokens to every session, about $0.0141 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.