next16-claude-starter: Instructions file for Codex

AGENTS.md

next16-claude-starter AGENTS.md is an instructions file for Codex, OpenCode from textura-agency/next16-claude-starter. It costs 2,420 tokens per session, scanned A, original, Unlicense.

A project-specific guide for working on textura-agency/next16-claude-starter, including its documentation, commands, project structure, and rules for making changes. It explains that this project's version of Next.js differs from familiar conventions.

In plain words
What is it for?
Use it before building pages, animations, database work, content-management features, migrations, or SEO changes in this repository.
Why use it?
It reduces the risk of applying outdated framework assumptions or changing the project without first consulting its single source of truth.

Instructions file for CodexOpenCode

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

This is textura-agency/next16-claude-starter's own configuration. It tells Codex and OpenCode how to work on next16-claude-starter 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 next16-claude-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to textura-agency/next16-claude-starter. 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/textura-agency/next16-claude-starter/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/textura-agency/next16-claude-starter

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 next16-claude-starter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/textura-agency/next16-claude-starter/agents-md/github.svg)](https://agentmods.dev/instructions/textura-agency/next16-claude-starter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/textura-agency/next16-claude-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/textura-agency/next16-claude-starter/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 next16-claude-starter AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/textura-agency/next16-claude-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/textura-agency/next16-claude-starter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,420 This file is loaded in full into every session.
When invoked 2,420 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 $0.02420 $0.02420
Opus 5.5 $0.00968 $0.00968
Sonnet 5.5 $0.00484 $0.00484
Haiku 4.5 $0.00242 $0.00242

Measured 13d ago against content hash 7b49802f1ae3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

next16-claude-starter 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 13d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide — next16-claude-starter

This is NOT the Next.js you know

This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Heed deprecation notices and verify against the docs before writing routing or framework code.

Documentation lives in the vault

All project documentation is the obsidian/ Obsidian vault — it is the single source of truth for how this project is built.

Before working, read:

  • obsidian/README.md — Map of Content (index of every doc)
  • obsidian/workflows/ai-agent-guide.md — full rules of engagement
  • The relevant topic note (e.g. frontend/animation-system.md before animation work, workflows/new-page.md before building a page)
  • Before optimising anything: obsidian/knowledge/fix-catalog.md and obsidian/knowledge/pitfalls.md — fixes measured on many production sites, and the traps that misled the measurements. Try rule entries first.

Commands, skills and agents live in .claude/ and are mapped in obsidian/workflows/agent-harness.md. Common entry points: /new-page, /section, /qa, /ship, /cms, /db, /seo, /seo-grow, /migrate-site, /perf, /load, /mobile. The testing tools are tools/qa/* (yarn qa:*) — see tools/qa/README.md and obsidian/workflows/testing-pipeline.md.

Notes link each other with [[wikilinks]] — follow them to navigate.

Hard rules (never violate)

  1. All motion is spring-based — @react-spring/web via the components in src/components/animation/springs/. Text animation uses spring-text-engine. No CSS keyframes, no framer-motion. One exception: CSS transition-* is allowed for simple discrete state changes (hover/focus colour, opacity, border, small nudges) with token-backed timing — duration-[var(--duration-fast)] ease-entrance. Everything scroll-driven, revealing, staggered, or layout-affecting stays a spring. See obsidian/frontend/design-system.md.
  2. Do not modify src/components/animation/springs/ or src/hooks/animation/ without explicit sign-off — they are the vendored animation engine. One authorized performance refactor has been made (see decisions-log.md ADR-0009); they remain protected by default.
  3. Never mode="manual" on TextEngine — use always / once / forward / progress. TextEngine's container is flex, so text-align alone cannot align it — always pair text-center with justify-center (etc.) on the tag. And overflow clips to the line-height box, so keep leading ≥ 1.1 (leading-display); never leading-none with overflow, or glyphs get shaved. See obsidian/frontend/text-engine.md.
  4. No hardcoded values — design tokens in globals.css for styles; props/hooks for content. No raw hex/px in class names. Tokens follow a strict three-tier convention (--raw-* primitive → semantic role → @theme binding) that is identical across every project built from this starter — see obsidian/frontend/design-system.md.
  5. Routes delegate to views — app/**/page.tsx imports only from src/views/.
  6. Server Components by default; add "use client" only at the leaves.
  7. No any. Type everything. Run yarn lint before finishing.
  8. Navigation — standard next/link <Link> and next/navigation useRouter.
  9. API & secrets — external/third-party calls run server-side in app/api/**/route.ts; secret keys are server-only env vars (never NEXT_PUBLIC_, read via src/env.ts). The browser only calls same-origin /api/*. Validate input with zod; return the { data } / { error } envelope. See obsidian/backend/api-architecture.md.
  10. Semantic, SEO-correct HTML — native elements over divs, one <h1> + a clean heading outline, named landmarks, real button/a, alt text, JSON-LD (not microdata), semantic tag on animation components. See obsidian/frontend/html-semantics.md.
  11. Verify before reporting done. yarn verify (.claude/scripts/verify.sh, zero FAILs) + yarn lint + yarn build after any code change, and the qa-verify skill after any UI change. See obsidian/workflows/qa-verification.md.
  12. CMS & database are Payload + Supabase, added per project — not shipped in the starter. Use the payload-cms / supabase-db skills; see obsidian/backend/cms-payload.md. Note middleware.ts does not exist in Next 16 — it is proxy.ts.
  13. Performance → measure, never guess. Build, measure, attribute, fix one thing, re-measure. Never report a performance win you did not measure. Records come from tools/qa/* against a production build (yarn build && yarn start, never next dev), PC and mobile, median of 3+ runs, confirmed on the real host. The bar: Performance ≥ 90 on PC and mobile; Accessibility, Best Practices and SEO 100 — for people and for the robot form; scroll ideal (no frame > 50 ms) on PC and phone, first and second visit. Run yarn qa:setup once per machine. Two skills, by what is slow:
    • Load — Lighthouse scores, Core Web Vitals, accessibility, SEO → optimize-load (yarn qa:lh, yarn qa:axe). See obsidian/workflows/optimize-load.md.
    • After load — scroll jank, micro-freezes, dropped frames → optimize-performance (yarn qa:scroll, --first-scroll after a loader). Check first whether the first scroll is worse than the second; Lighthouse never scrolls and cannot see this. See obsidian/workflows/optimize-performance.md.
  14. 3D performance → use the skill. If the request is about performance, jank, or shipping readiness and the project renders a three.js / WebGL scene (three in package.json, or a canvas with a render loop), invoke the optimize-3d-scene skill first and follow its order of fixes — don't improvise one. See obsidian/workflows/optimize-3d-scene.md.
  15. Routes stay static; crawlers get the robot form. Never headers(), cookies() or isBot() in a page, view, layout, lib/site or the SEO helpers — src/proxy.ts routes bots (search and AI crawlers) to /robot-view. Don't add an app/loading.tsx without a real skeleton (an empty one hides the page from non-JS crawlers). Every page is registered in src/lib/routes.ts (sitemap, /llms.txt, breadcrumbs read it); yarn qa:seo checks the served values. The consent banner is server-rendered — it is often the phone's LCP. See obsidian/frontend/robot-form.md, .claude/rules/seo-robot.md.
  16. Loops and frames. Every looping spring reads useMotionOff() (reduced motion and the robot form would otherwise freeze the page). Per-frame code scales by dt in seconds (src/lib/scene/per-frame.ts) — 120 Hz phones run per-frame steps twice as fast. No fixed frame cap on phones (it reads as choppy); desktop scenes may gate the draw at ~60 fps (createDrawGate). Never stop drawing a canvas that is on screen; recover lost WebGL contexts (src/lib/scene/webgl-context.ts). See .claude/rules/scenes.md.
  17. Phones are checked on phones. Lab tools miss what a person sees on an iPhone: Safari's toolbar resizing the viewport, 120 Hz speed, lost GPU contexts, menus under the bottom bar, dark-mode overlays, touch sliders. Full-screen scene boxes use the large viewport (<SceneViewport>); menus use h-dvh + the safe area, their own colour token and a portal under <body>. Something wrong on a phone → mobile-device-qa (/mobile, yarn qa:ios, qa:fps, qa:context, qa:webkit — WebKit for iOS-only bugs). Before calling UI done, have it opened on a real phone; if that didn't happen, say so. See obsidian/workflows/mobile-device-qa.md.
  18. No placeholders at launch. src/lib/site.ts ships TODO: values on purpose: every build warns and a Vercel production build fails until the name, description, URL and brand assets are filled (brand kit: yarn qa:brand). See obsidian/frontend/seo-metadata.md.

Read the full file on GitHub · 144 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. 13d ago Changed · +2 lines · +44 tokens per session 7b49802f1ae3
  2. 21d ago Changed · +39 lines · +783 tokens per session cc492637419b
  3. 1mo ago Changed · +3 lines · +59 tokens per session 4bfd9a1b0652
  4. 1mo ago Changed · +8 lines · +135 tokens per session ec002c3a42a9
  5. 1mo ago First seen · 92 lines · 1,399 tokens per session scan A 0608d9ad6039

Subscribe to this mod's changes

next16-claude-starter AGENTS.md is an instructions file published in the GitHub repository textura-agency/next16-claude-starter (139 stars, last pushed 13d ago), licensed Unlicense. It adds 2,420 tokens to every session, about $0.0097 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

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 · 9,715 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 · 7,786 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