Use it when changing Co-Op’s backend or desktop workflows, configuring local or customer-provided AI models, or checking licence activation and related business rules.

It explains which work must stay on the customer’s computer, how cloud licensing works, and which sensitive information must not be logged.

How Afnanksalal/co-op configures Codex and OpenCode

Q: What is co-op AGENTS.md?

A repository-specific instruction file for Co-Op, local-first business management software with a cloud service for accounts, licences, and payments.

Reuse

Borrowing it

Nothing to install: this file belongs to Afnanksalal/co-op. 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/Afnanksalal/co-op/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Afnanksalal/co-op

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/afnanksalal/co-op/agents-md/github.svg)](https://agentmods.dev/instructions/afnanksalal/co-op/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/afnanksalal/co-op/agents-md"><img src="https://agentmods.dev/badge/instructions/afnanksalal/co-op/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/afnanksalal/co-op/agents-md"><img src="https://agentmods.dev/badge/instructions/afnanksalal/co-op/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,095 This file is loaded in full into every session.

When invoked 1,095 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.

Model	Per session	Once invoked
Fable 5.1	$0.01095	$0.01095
Opus 5.5	$0.00438	$0.00438
Sonnet 5.5	$0.00219	$0.00219
Haiku 4.5	$0.00110	$0.00110

Measured 2mo ago against content hash ac0567f68608, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

co-op 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 2mo 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Co-Op Agent Guide

This guide is for humans and automated coding agents working in this repository. Treat it as the repo-level operating contract.

Product Contract

Co-Op is local-first business management software with a cloud license control plane.

The cloud backend owns account identity, license generation, activation, heartbeat, revocation, and payment entitlement hooks.
The installed desktop app owns business workflow execution, provider configuration, local run history, and local company data.
Cloud services must not become mandatory for business workflows.
Customer model usage must be explicit: Ollama for local execution or an OpenAI-compatible bring-your-own-key endpoint selected by the customer.
Council-style review is a gated review mode, not the default execution strategy.
Raw license keys, activation tokens, provider keys, workflow prompts, and customer outputs must not be logged.

Workspace Map

backend/ is the NestJS license control plane.
backend/src/modules/licenses/ contains activation, heartbeat, deactivation, and admin license generation.
backend/src/database/schema/licenses.schema.ts is the source of truth for the cloud license schema.
frontend/ is the Next.js public site, account UI, admin license UI, and desktop UI shell.
frontend/src-tauri/ is the Rust Tauri runtime that stores local activation state, model routing settings, and workflow run history.
docs/ contains durable architecture, licensing, orchestration, and operations references.
Hosted production web builds must not expose the installed desktop shell. /desktop and /local routes are for Tauri/static desktop builds and local development only.

Required Checks

Run the narrowest relevant checks while iterating. Before shipping product changes, run the full suite:

cd backend
npm test
npm run build
npm audit --audit-level=low

cd ../frontend
npm run typecheck
npm run build
npm run build:tauri
npm audit --audit-level=low
npm run audit:rust

cd src-tauri
cargo test
cargo clippy --all-targets -- -D warnings

Read the full file on GitHub · 71 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.

2mo ago First seen · 71 lines · 1,095 tokens per session scan A ac0567f68608

Subscribe to this mod's changes

co-op AGENTS.md is an instructions file published in the GitHub repository Afnanksalal/co-op (5 stars, last pushed 4d ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0044 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 2026-08-31.

ai-agents ai-assistant fastapi fintech gemini groq

co-op AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
co-op AGENTS.mdAfnanksalal/co-op	Instructions file	5	4d ago	MIT	A	1,095	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

co-op: Instructions file for Codex