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/muzafferkadir/nextjs-loop-engineering-starter/agents-mdgit clone --depth 1 https://github.com/muzafferkadir/nextjs-loop-engineering-starterWrote 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/muzafferkadir/nextjs-loop-engineering-starter/agents-md)<a href="https://agentmods.dev/instructions/muzafferkadir/nextjs-loop-engineering-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/muzafferkadir/nextjs-loop-engineering-starter/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 | $0.01479 | $0.01479 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
nextjs-loop-engineering-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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Instructions for AI Agents
How to Start a Loop
See README.md → "Developing with the Loop" for the Report/Build mode
commands. Skills
live in .claude/skills/<name>/SKILL.md.
Project Purpose
A task management web application built with Next.js and developed through loop engineering. Treat this as a real product codebase: the backlog in BACKLOG.md defines what to build next, and every change goes through the verifier pipeline. Whatever the product owner puts in BACKLOG.md is the product — build that.
Stack
Next.js 15 (App Router) · React 19 · TypeScript (strict)
Tailwind CSS 4 + shadcn/ui conventions (components.json is configured)
SQLite + Drizzle ORM (zero external services)
Vitest (unit) · Playwright (e2e, deterministic config)
Commands
pnpm db:reset # push schema + deterministic seed — run once after clone
pnpm e2e # Playwright e2e (starts its own server, reseeds DB)
pnpm verify # THE verification pipeline — same as CI
pnpm snap [routes] # screenshot pages for visual inspection (dev server must run)
Code Rules
TypeScript
strict: trueandnoUncheckedIndexedAccess: true— never useany(the verifier rejects diffs containingany)- Validate every external input (form data, search params) with Zod
Next.js
- Server Components by default — add
"use client"only where the component needs state, effects, or event handlers - Mutations go through Server Actions in
actions.tsfiles colocated with the route (seesrc/app/tasks/actions.tsfor the reference pattern: auth check → Zod parse → ownership check → mutate →revalidatePath) - Every route with async data gets
loading.tsxanderror.tsx(seesrc/app/tasks/for the reference implementation) - Auth: call
getCurrentUser()from@/lib/authin server code. Never editsrc/lib/auth.ts— it is denylisted.
Database (Drizzle + SQLite)
- Schema:
src/db/schema.ts. Always query throughdbfrom@/db/client - Schema change flow: edit schema →
pnpm db:pushlocally → note in the PR that a migration is needed. Schema changes always need human review - Deletes are soft (
deletedAt) — follow the pattern intasks - Never edit
src/db/seed.tsrandomness rules: seeds stay deterministic (fixed IDs, fixed dates), e2e depends on it
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.
- 4d ago First seen · 134 lines · 1,479 tokens per session scan A 99dc535789a3
nextjs-loop-engineering-starter AGENTS.md is an instructions file published in the GitHub repository muzafferkadir/nextjs-loop-engineering-starter (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,479 tokens to every session, about $0.0074 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
forge CLAUDE.md
Instructions for firatcand/forge, covering forge, stack, commands, conventions and critical paths.
forge AGENTS.md
Instructions for firatcand/forge, covering forge, stack, commands, conventions and critical paths.
odin-codex-plugin AGENTS.md
AGENTS.md instructions for OutlineDriven/odin-codex-plugin, covering codex coding agent adherences, token-efficient cli output, tool hierarchy, core system & file ops and search & discovery.
baro AGENTS.md
AGENTS.md instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.
baro CLAUDE.md
Claude Code instructions for jigjoy-ai/baro, covering claude.md, project overview, tech stack, directory structure and build commands.
RemoClaw CLAUDE.md
Instructions for quangtam/RemoClaw, covering remoclaw — agent context, what is this?, architecture, file structure and how to run.