agentmods.dev

Novel: Instructions file for Codex

AGENTS.md

Novel AGENTS.md is an instructions file for Codex, OpenCode from VaIOReTto1/Novel. It costs 1,086 tokens per session, scanned A, original, MIT.

Repository instructions for Novel, a React Native app, explaining which documents and files agents should read first and which sources take priority when information conflicts.

In plain words
What is it for?
Use them when working on Novel's source code, Android setup, automated quality checks, testing harness, or refactoring and rollback records.
Why use it?
They help an agent find current project and refactoring guidance instead of relying on older general documentation.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is VaIOReTto1/Novel's own configuration. It tells Codex and OpenCode how to work on Novel 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 Novel configures →

not rated 26repo 7mo ago A scan 1,086 tokens original MIT
View source ↗ VaIOReTto1/Novel
Reuse

Borrowing it

Nothing to install: this file belongs to VaIOReTto1/Novel. 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/VaIOReTto1/Novel/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/VaIOReTto1/Novel

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 Novel AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vaioretto1/novel/agents-md/github.svg)](https://agentmods.dev/instructions/vaioretto1/novel/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vaioretto1/novel/agents-md"><img src="https://agentmods.dev/badge/instructions/vaioretto1/novel/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 Novel AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vaioretto1/novel/agents-md"><img src="https://agentmods.dev/badge/instructions/vaioretto1/novel/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,086 This file is loaded in full into every session.
When invoked 1,086 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 $0.01086 $0.01086
Opus 5.5 $0.00434 $0.00434
Sonnet 5.5 $0.00217 $0.00217
Haiku 4.5 $0.00109 $0.00109

Measured 2mo ago against content hash 76a504f9b239, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Novel 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 2mo 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Novel Agent Guide

Role Of This File

  • This file is a directory, not an encyclopedia.
  • Read the next linked document only when you need that extra context.
  • Do not treat this file as the final source of truth for refactor status.

First Read Order

  1. ARCHITECTURE.md
  2. docs/harness/README.md
  3. docs/harness/current-focus.md
  4. If the task touches refactor stages, docs/refactor/README.md
  5. If the task touches evidence, rollback, or closeout, follow the linked refactor docs from that control panel

Source Of Truth Priority

  1. Executable repo truth
    • package.json
    • android/settings.gradle
    • android/app/build.gradle
    • .github/workflows/quality-gates.yml
    • current source files and tests
  2. Refactor authority
    • docs/refactor/README.md
    • linked validation boards
    • linked closeout docs
    • docs/refactor/tracking/decision-log.md
    • docs/refactor/tracking/rollback-index.md
  3. Harness memory layer
    • docs/harness/current-focus.md
    • docs/harness/session-log.md
    • docs/harness/generated/workspace-snapshot.md
  4. Secondary docs that may lag
    • root README.md
    • .trae/rules/project_rules.md

Repo Shape

  • React Native app code lives in src/**
  • Android code lives in android/app, android/core-*, android/feature-*, and android/macrobenchmark
  • Jest tests live in __tests__/**
  • Refactor control plane lives in docs/refactor/**
  • Harness control plane lives in docs/harness/**

Task Routing

  • Architecture or boundary questions:
  • "What is happening now?" questions:
  • Stage status, closeout, rollback, decision history:
  • Android module graph:
    • android/settings.gradle
    • docs/refactor/phase-5/module-graph-current-state.md
  • RN bridge contracts:
    • src/utils/bridge/**
    • android/app/src/main/java/com/novel/rn/**
    • __tests__/bridge/**
  • Verification command lookup:
    • docs/harness/references/verification.md
  • Active execution plans:
    • docs/harness/exec-plans/active/index.md

Read the full file on GitHub · 105 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. 2mo ago First seen · 105 lines · 1,086 tokens per session scan A 76a504f9b239

Subscribe to this mod's changes

Novel AGENTS.md is an instructions file published in the GitHub repository VaIOReTto1/Novel (26 stars, last pushed 7mo ago), licensed MIT. It adds 1,086 tokens to every session, about $0.0043 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

Novel AGENTS.md compared with instructions from other repositories

Novel AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Novel AGENTS.mdVaIOReTto1/NovelInstructions file267mo agoMITA1,086Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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