agent-stack-template AGENTS.md

A set of project instructions for a production-style multi-tenant web application template, where one application serves multiple organizations or customers. It tells agents how to classify requests and which guides to read.

In plain words
What is it for?
Renaming and adapting the template, choosing the right workflow for a request, and using the included projects feature as a reference before removing it.
Why use it?
It gives agents consistent rules for working in an unfamiliar template and helps prevent them from treating its custom Next.js setup like a standard project.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/krivoox/agent-stack-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/krivoox/agent-stack-template

Made for: Codex, OpenCode.

Per session 2,198 This file is loaded in full into every session.
When invoked 2,198 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02198 $0.02198
Opus 5 $0.01099 $0.01099
Sonnet 5 $0.00440 $0.00440
Haiku 4.5 $0.00220 $0.00220

Measured 2d ago against content hash be22bee4fb5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-stack-template 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 2d 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 · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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. Read the relevant guide in node_modules/next/dist/docs/ before writing any code. Heed deprecation notices.

Agent guide

Rename this product in src/lib/app-config.ts, package.json and this file. Everything else is already generic.

What this repository is

A production-shaped starting point for a multi-tenant web application, built so that coding agents produce consistent work without being told the same things twice. Conventions live in files an agent reads automatically, not in a person's head.

The included projects feature is a reference vertical slice, not a product. Read it, copy its shape, then delete it.

Every turn

Classify before opening a file. Open one matching guide. Do not read the other playbooks, and do not start from the layer walkthrough until the type is known.

The request is… Do this Do not
A problem, audience or outcome, no spec product-manager → spec Draft write product code
Spec exists but is Draft, or has open questions resolve with the user; domain-architect if the rules are non-trivial write product code
Spec Accepted or Shipped, new behaviour with a domain rule new-feature.md skip the spec
Spec Accepted or Shipped, new behaviour with no domain rule (wiring, copy, layout only) new-feature.md, skip domain tests and domain/ invent a domain/ function so TDD has a target
Spec and code disagree say which is wrong; fix that one invent a third rule
Current behaviour is wrong bugfix.md start a feature
Same behaviour, new shape refactor.md change a spec rule
Tooling, deps, CI, env, docs-only chore.md sneak in behaviour; write a domain test
Copy, layout, existing actions ui-ux-developer put rules in React; TDD the markup
Infra, migrations, deploy, secrets devops-engineer run destructive commands unasked
The change does not touch domain/ and adds no business rule TDD does not apply. npm run verify is the gate invent a test or a domain wrapper

Read the full file on GitHub · 170 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. 2d ago First seen · 170 lines · 2,198 tokens per session scan A be22bee4fb5c

Subscribe to this mod's changes

agent-stack-template AGENTS.md is an instructions file published in the GitHub repository krivoox/agent-stack-template (31 stars, last pushed 12d ago), licensed MIT. It adds 2,198 tokens to every session, about $0.0110 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.

Related

Other instructions, from other repositories