What is keypro-cli AGENTS.md?

Project instructions for KeyPro CLI, a command-line tool for buying and managing business software licences from KeyPro.hu.

Configuring the KeyPro account, checking identity, placing licence orders, interpreting command results, and handling product options such as tiers or editions.

They explain the setup, authentication, structured JSON output, error handling, and ordering rules an AI agent must follow.

keypro-cli AGENTS.md — Instructions file by InstaSoft-hu

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/instasoft-hu/keypro-cli/agents-md

Clone the repo

git clone --depth 1 https://github.com/InstaSoft-hu/keypro-cli

Made for: Codex, OpenCode.

Per session 4,817 This file is loaded in full into every session.

When invoked 4,817 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.04817	$0.04817
Opus 5	$0.02409	$0.02409
Sonnet 5	$0.00963	$0.00963
Haiku 4.5	$0.00482	$0.00482

Measured yesterday against content hash a56808c7d916, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

keypro-cli AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`keypro products images 123 | xargs -n1 curl -O`.

AGENTS.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KeyPro CLI - AI agent guide

Magyar: ez a KeyPro.hu B2B licencshop parancssori eszkoze; az alabbi angol utmutato AI-agenteknek (ChatGPT, Claude, Gemini, Codex, OpenCode) szol.

Setup

The user needs a KeyPro account (approved reseller) and an API key. Easiest: keypro setup - interactive wizard (asks the server, then API key [default] or email+password). Alternatives:
- keypro login (email + password, mints + stores a fresh key)
- a key made on the website under "API, MCP és CLI" (https://keypro.hu/api), stored via keypro config set api-key kp_live_..., the KEYPRO_API_KEY env var (recommended for agents), or ~/.config/keypro/config.json
API base URL: production is the default. For the dev site use keypro setup, KEYPRO_API_BASE=https://dev.keypro.hu, or keypro config set api-base ....
Verify with: keypro whoami --json

Output contract

Every command supports --json: machine-readable data on stdout.
Errors go to stderr; in --json mode they are JSON with a stable error.code (snake_case English). Key on code, not on the Hungarian message.
Exit codes: 0 success, 1 API/business error, 2 usage error, 3 auth error.

Ordering flow (IMPORTANT)

Ordering is a two-step preview + confirm flow to prevent accidental orders:

keypro order preview --item SKU=QTY --payment bacs --json Returns priced lines, fees, shipping, totals and a confirmToken (valid 15 minutes, bound to items + payment method + gross total). ALWAYS show the totals to the user before ordering.
keypro order create --item SKU=QTY --payment bacs --yes --json Without --yes the command only prints the preview and exits with code 1. With --yes it re-runs the preview and submits with the fresh confirmToken. If prices changed between preview and create, the server rejects with confirm_token_invalid and returns the new totals in error.details - re-run preview and show the user the new total.
Retries: pass --idempotency-key <any-unique-string> - the same key never creates a second order (the response has idempotentReplay: true).

Read the full file on GitHub · 322 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.

yesterday First seen · 322 lines · 4,817 tokens per session scan A a56808c7d916

Subscribe to this mod's changes

keypro-cli AGENTS.md is an instructions file published in the GitHub repository InstaSoft-hu/keypro-cli (0 stars, last pushed 12d ago), licensed MIT. It adds 4,817 tokens to every session, about $0.0241 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

keypro-cli AGENTS.md