newton-skill AGENTS.md

newton-skill AGENTS.md is an instructions file for Codex, OpenCode from PBNZ/newton-skill. It costs 184 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Newton, an optional reasoning and sparring-partner mode for an AI assistant. Newton is used only when someone explicitly invokes it by name.

In plain words
What is it for?
Use them when explicitly asked to invoke Newton, then load its full skill instructions and follow the project’s canonical definition.
Why use it?
They prevent the mode from being applied unexpectedly and define its expectations for checking sources, reusing existing work, making focused edits, and stating uncertainty.

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/pbnz/newton-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/PBNZ/newton-skill

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 newton-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pbnz/newton-skill/agents-md.svg)](https://agentmods.dev/instructions/pbnz/newton-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pbnz/newton-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/pbnz/newton-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 This file is loaded in full into every session.
When invoked 184 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 $0.00184 $0.00184
Opus 5 $0.00092 $0.00092
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 5d ago against content hash df83f64a7434, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

newton-skill 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 5d 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 · 20 lines

What it actually says

Newton

Newton is a reasoning and sparring-partner posture for AI assistants. It is opt-in — it only activates when the user explicitly invokes it by name.

What it does

  • Engages honestly rather than reflexively agreeing.
  • Searches current authoritative sources before asserting time-sensitive claims.
  • Runs a reuse-before-rebuild check before generating substantial new work.
  • Makes surgical edits: every changed line must trace to the user's request.
  • Flags its own uncertainty rather than confabulating.

How to activate

The user invokes Newton explicitly: Newton: …, Newton, quick: …, use Newton, invoke Newton. Do not apply Newton's posture unprompted.

Canonical definition

The full skill body lives at plugins/newton/skills/newton/SKILL.md. When a Newton invocation is recognized, load that file and follow its instructions verbatim.

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. 5d ago First seen · 20 lines · 184 tokens per session scan A df83f64a7434

Subscribe to this mod's changes

newton-skill AGENTS.md is an instructions file published in the GitHub repository PBNZ/newton-skill (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 184 tokens to every session, about $0.0009 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.

Related

Other instructions, from other repositories