neuraforge-ai: Instructions file for Codex

AGENTS.md

neuraforge-ai AGENTS.md is an instructions file for Codex, OpenCode from vikisingh23/neuraforge-ai. It costs 1,962 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for developing the NeuraForge AI platform, including required coding practices and review steps.

In plain words
What is it for?
Use them before generating, reviewing, debugging, or scaffolding code in that project; they require searching the codebase and presenting a plan before editing.
Why use it?
They help prevent duplicate code, oversized classes, missing pagination, inconsistent errors, and incomplete audit fields.

Instructions file for CodexOpenCode

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

This is vikisingh23/neuraforge-ai's own configuration. It tells Codex and OpenCode how to work on neuraforge-ai 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 neuraforge-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vikisingh23/neuraforge-ai. 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/vikisingh23/neuraforge-ai/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/vikisingh23/neuraforge-ai

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 neuraforge-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vikisingh23/neuraforge-ai/agents-md/github.svg)](https://agentmods.dev/instructions/vikisingh23/neuraforge-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vikisingh23/neuraforge-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/vikisingh23/neuraforge-ai/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 neuraforge-ai AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vikisingh23/neuraforge-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/vikisingh23/neuraforge-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,962 This file is loaded in full into every session.
When invoked 1,962 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 $0.01962 $0.01962
Opus 5.5 $0.00785 $0.00785
Sonnet 5.5 $0.00392 $0.00392
Haiku 4.5 $0.00196 $0.00196

Measured 17d ago against content hash c78342bde1c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

neuraforge-ai 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 17d 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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeuraForge AI — Agent Instructions

You have access to the NeuraForge AI development platform. Use these agents and rules when working on this codebase.

How to Use

When the user asks you to generate code, review code, debug, scaffold, or any development task — follow the appropriate agent instructions below. Always search the codebase before generating new code.

Plan Before Acting

Before writing any code:

  1. Search the codebase for existing similar code — use the codebase-graph skill (graphify) if it's available, for anything beyond a trivial grep
  2. Identify what to reuse, extend, or refactor
  3. Present a brief plan and wait for approval
  4. Then execute

Feedback Protocol (MANDATORY — how agents learn)

Read rules/core/FEEDBACK_PROTOCOL.md in full. Every code-generating agent must:

  1. Before generating — load rules/anti-patterns/{stack}.md and apply every rule listed
  2. Before generating — check if .neuraforge/lessons.md exists; if so, read and apply project-specific rules
  3. After generating — write a feedback log to .neuraforge/feedback/{agent}-{YYYYMMDD}-{id}.md
  4. Tell the user — at the end of every response, show the feedback log path and how to flag mistakes

This is how the agents improve. Every corrected feedback item becomes a new anti-pattern rule.

Minimal Solution Principle (MANDATORY — how much to generate)

Read rules/core/MINIMAL_SOLUTION.md in full before generating. Work down its ladder — does this need to exist, does it already exist, does the framework already do it, is there an approved dependency, can an existing file absorb it — and stop at the first rung that resolves the request. The "never skip" list in that file (audit fields, decimal money, validation, idempotency, pagination, auth, UX states) stays mandatory regardless of how small the request is.

Architecture Principles (enforce on ALL code)

  • Data fetching at the leaf level — each component/widget fetches its own data, no parent prop-drilling
  • Reuse → Extend → Refactor → Create — never duplicate. Search first.
  • No god classes — controllers <150 lines, services <300, components <150
  • Composition over inheritance — DI composition, max 1 level of inheritance
  • Consistent error handling — standard response envelope, domain exceptions
  • Audit everything — createdBy, modifiedBy, createdAt, modifiedAt, soft deletes
  • Pagination on all lists — never return unbounded collections
  • Loading / Error / Empty states — on every data-driven screen
  • API URL paths: always lowercase-hyphenated (kebab-case) — /api/v1/bank-accounts, /api/v1/transaction-history, NOT /api/v1/BankAccounts or /api/v1/bankAccounts. Enforced across ALL stacks (.NET, NestJS, Django, Spring Boot, React, RN, Flutter).

Read the full file on GitHub · 146 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. 17d ago Changed · +8 lines · +188 tokens per session c78342bde1c6
  2. 21d ago Changed · +35 lines · +593 tokens per session 47dda82c6ada
  3. 1mo ago First seen · 103 lines · 1,181 tokens per session scan A 4af296b50855

Subscribe to this mod's changes

neuraforge-ai AGENTS.md is an instructions file published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,962 tokens to every session, about $0.0078 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 2026-08-31.

Related

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).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,549 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens