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/nixrajput/portfolio-nextjs/agents-mdgit clone --depth 1 https://github.com/nixrajput/portfolio-nextjsWrote 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/nixrajput/portfolio-nextjs/agents-md)<a href="https://agentmods.dev/instructions/nixrajput/portfolio-nextjs/agents-md"><img src="https://agentmods.dev/badge/instructions/nixrajput/portfolio-nextjs/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 5.1 | $0.03073 | $0.03073 |
| Opus 5 | $0.01537 | $0.01537 |
| Sonnet 5 | $0.00615 | $0.00615 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
portfolio-nextjs 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 6d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Guidelines
Last updated: 2026-08-17
The working-discipline and multi-agent-safety rules that used to live here were a verbatim copy of ~/.claude/CLAUDE.md, which is already loaded into every session. They were deleted rather than maintained in two places. This file now carries only what is true of this repo and cannot be derived from reading it quickly.
Project
Personal portfolio and site for Nikhil Rajput, deployed at https://nixrajput.com. A database-driven Next.js app: every section of the homepage is content managed through an authenticated admin area rather than hardcoded.
| Area | Detail |
|---|---|
| Runtime | Bun (lockfile bun.lockb), TypeScript, ESM |
| Framework | Next.js 16 (App Router) + React 19 |
| Styling | Tailwind CSS v4 (CSS-first @theme, no tailwind.config.js) |
| Data | Drizzle ORM + Postgres; migrations in drizzle/ |
| Auth | NextAuth v5 (beta), admin-only |
| Platform | Vercel - Blob (uploads), Analytics, Speed Insights |
| Resend (testimonial notifications) | |
| Lint / format | ESLint + Prettier - double quotes, semicolons, 100 columns |
| Tests | Vitest (unit/component) + Playwright (e2e in e2e/) |
Layout
src/app/ App Router routes
src/app/admin/ authenticated CRUD for every content type
src/app/api/ route handlers (upload, revalidate, testimonials, auth)
src/app/globals.css the entire design system - read the notes inside before editing
src/components/home/ homepage sections (Hero, About, Projects, ...)
src/components/ui/ primitives (Button, Card, Section, dialog, avatar)
src/components/admin/ admin shell + the generic CRUD page/form machinery
src/db/schema.ts Drizzle schema, single source of truth for content types
src/db/seed.ts `bun run db:seed`
src/lib/queries.ts the homepage's data reads
src/lib/projects.ts merges DB curation rows with cached GitHub stats
src/lib/github-cache.ts 24h-TTL GitHub cache, never throws
src/lib/seo/site.ts SITE constants (canonical URL, title, description)
scripts/ check-routes and check-vitals
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.
- 6d ago First seen · 126 lines · 3,073 tokens per session scan A b7b0c3df4e72
portfolio-nextjs AGENTS.md is an instructions file published in the GitHub repository nixrajput/portfolio-nextjs (144 stars, last pushed 19d ago), licensed MIT. It adds 3,073 tokens to every session, about $0.0154 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 2026-08-30.
Other instructions, from other repositories
viperadnan-git.github.io CLAUDE.md
Claude Code instructions for viperadnan-git/viperadnan-git.github.io, covering portfolio project - claude context, project overview, tech stack, project structure and data loading system.
sagarshah.dev AGENTS.md
Instructions for shahsagarm/sagarshah.dev, covering this is not the next.js you know, sagarshah.dev v2, commands, token contract (strongest rule in the repo) and architecture.
my-portfolio CLAUDE.md
Claude Code instructions for NguyenNguyen0/my-portfolio, covering claude.md, commands and architecture.
sagarshah.dev CLAUDE.md
Instructions for shahsagarm/sagarshah.dev: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
trigsight AGENTS.md
AGENTS.md instructions for Raghu23-dev/trigsight: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo…
trigsight CLAUDE.md
Claude Code instructions for Raghu23-dev/trigsight, a project described as: Portfolio with an AI assistant that cannot make a claim it can't prove — every citation is bound at build time to the exact supporting sentence, or the build fails.