agent-nudge AGENTS.md

agent-nudge AGENTS.md is an instructions file for Codex, OpenCode from manazoid4/agent-nudge. It costs 160 tokens per session, scanned A, original, MIT.

A set of repository instructions for agent-nudge, a local-first tool that checks an AI coding agent's context and possible file conflicts before edits.

In plain words
What is it for?
Use it when modifying agent-nudge to choose the correct branches and commands, keep relevance decisions explainable, and verify changes with its documented test and build workflows.
Why use it?
It tells agents how to preserve project isolation, avoid hidden data collection or configuration changes, and follow the project's required checks.

Instructions file for CodexOpenCode

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/manazoid4/agent-nudge/agents-md
Clone the repo
git clone --depth 1 https://github.com/manazoid4/agent-nudge

Made for: 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 agent-nudge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/manazoid4/agent-nudge/agents-md.svg)](https://agentmods.dev/instructions/manazoid4/agent-nudge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/manazoid4/agent-nudge/agents-md"><img src="https://agentmods.dev/badge/instructions/manazoid4/agent-nudge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 160 This file is loaded in full into every session.
When invoked 160 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 $0.00160 $0.00160
Opus 5 $0.00080 $0.00080
Sonnet 5 $0.00032 $0.00032
Haiku 4.5 $0.00016 $0.00016

Measured 3d ago against content hash 1b865d981e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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.

AGENTS.md · 11 lines

What it actually says

Agent instructions

  • Work on agents/* branches; never push directly to main.
  • Preserve local-first operation and project isolation.
  • Never add transcript capture, hidden telemetry, or silent configuration writes.
  • Keep relevance deterministic and explainable unless a future feature is clearly optional.
  • Run lint, format check, typecheck, unit, integration, E2E, build, demo, doctor, and Windows packaging before completion claims.
  • Product/design context lives in PRODUCT.md and DESIGN.md.
  • Brief Compiler planning and dogfood artifacts live under docs/dogfood/.
  • Useful compiler workflows already in repo: agent-nudge brief, agent-nudge compile, npm run dev:daemon, npm run dev, and npm run doctor.
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. 3d ago First seen · 11 lines · 160 tokens per session scan A 1b865d981e6f

Subscribe to this mod's changes

agent-nudge AGENTS.md is an instructions file published in the GitHub repository manazoid4/agent-nudge (0 stars, last pushed 21d ago), licensed MIT. It adds 160 tokens to every session, about $0.0008 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.