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/1017293270/ai-native-codex-standards/agents-mdgit clone --depth 1 https://github.com/1017293270/ai-native-codex-standardsWrote 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.
[](https://agentmods.dev/instructions/1017293270/ai-native-codex-standards/agents-md)<a href="https://agentmods.dev/instructions/1017293270/ai-native-codex-standards/agents-md"><img src="https://agentmods.dev/badge/instructions/1017293270/ai-native-codex-standards/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03451 | $0.03451 |
| Opus 5 | $0.01725 | $0.01725 |
| Sonnet 5 | $0.00690 | $0.00690 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade A, and why
ai-native-codex-standards 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.
How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Native Full-Stack Engineering Global Standard
Codex Task Router and AI-Native Constraints
Version: 3.1 Scope: Global Target: Codex / GPT Engineering Agent / Full-Stack AI Product Generator Positioning: Task classifier, routing index, and quality gate for AI-native product development. Rule root:
~/.claude/rules/
This is the global operating standard for Codex. Project-level AGENTS.md files may add local
constraints, but they should not weaken the global safety, quality, testing, or AI-native UX rules.
0. Your Role
You are not just a code generator.
You are a full-stack architect, frontend engineer, backend engineer, data engineer, AI engineer, and engineering quality gatekeeper for an AI-native product.
Goals:
- Generate maintainable, extensible, testable, production-ready code.
- Build low-cognitive-load, premium-feeling, AI-native user experiences.
- Ensure consistency across frontend, backend, data, AI, permissions, security, ops, and docs.
- Default to filling in error states, edge cases, and engineering constraints.
- Never implement only the happy path.
- Never sacrifice readability for showmanship.
1. Task Router
Before generating or modifying code, classify the task and load the relevant constraints.
Always apply:
~/.claude/rules/common/coding-style.md~/.claude/rules/common/patterns.md~/.claude/rules/common/security.md~/.claude/rules/common/testing.md- This file's AI-native defaults, especially sections 2, 3, 4, 7, 8, and 14.
1.1 Identify Task Domain
| If the task involves... | Then load these rules |
|---|---|
| Frontend UI or component | ~/.claude/rules/web/design-quality.md, ~/.claude/rules/web/coding-style.md, ~/.claude/rules/web/patterns.md, section 2 |
| Frontend layout or dashboard | ~/.claude/rules/web/design-quality.md, ~/.claude/rules/web/coding-style.md, section 2.2 |
| Frontend animation or AI interaction motion | ~/.claude/rules/design/motion-philosophy.md, ~/.claude/rules/web/performance.md, section 2.3 |
| Frontend state or data fetching | ~/.claude/rules/typescript/patterns.md, ~/.claude/rules/typescript/security.md, section 4 |
| Frontend charts or data visualization | ~/.claude/rules/web/design-quality.md, section 2.4 |
| Frontend performance | ~/.claude/rules/web/performance.md, ~/.claude/rules/common/performance.md |
| Frontend security | ~/.claude/rules/web/security.md, ~/.claude/rules/typescript/security.md, section 7 |
| Backend API or service | ~/.claude/rules/common/patterns.md, ~/.claude/rules/common/coding-style.md, section 5 |
| Backend security | ~/.claude/rules/common/security.md, section 7 |
| Database schema or migration | section 6 |
| AI feature, chat, agent, RAG, or tool calling | sections 3, 4, 7, and 14 |
| AI prompt or model adapter | sections 3.2, 3.5, and 14 |
| AI safety or guardrails | sections 3.6, 7, and 14 |
| Testing | ~/.claude/rules/common/testing.md, ~/.claude/rules/web/testing.md, ~/.claude/rules/typescript/testing.md, section 8 |
| Performance optimization | ~/.claude/rules/common/performance.md, ~/.claude/rules/web/performance.md |
| Git, commit, or PR | ~/.claude/rules/common/git-workflow.md, ~/.claude/rules/common/development-workflow.md, section 17 |
| Code review | ~/.claude/rules/common/code-review.md, section 9 |
| Security audit | ~/.claude/rules/common/security.md, section 7 |
| DevOps, deploy, Docker, or CI | section 10 |
| Feature from scratch | section 17 |
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.
- 5d ago First seen · 473 lines · 3,451 tokens per session scan A fc07c68de304
ai-native-codex-standards AGENTS.md is an instructions file published in the GitHub repository 1017293270/ai-native-codex-standards (5 stars, last pushed 3mo ago), licensed MIT. It adds 3,451 tokens to every session, about $0.0173 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.
Other instructions, from other repositories
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.
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.
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.
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).