poland AGENTS.md

poland AGENTS.md is an instructions file for Codex, OpenCode from Xopoko/poland. It costs 905 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining the Poland add-on and its agent skills.

In plain words
What is it for?
They are for contributors editing the repository, packaging releases, and keeping administrative guidance safe and portable.
Why use it?
They set boundaries for official sources, privacy, public collaboration, supported agent hosts, and the types of tools the add-on may use.

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/xopoko/poland/agents-md
Clone the repo
git clone --depth 1 https://github.com/Xopoko/poland

Made for: Codex, OpenCode.

Per session 905 This file is loaded in full into every session.
When invoked 905 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 $0.00905 $0.00905
Opus 5 $0.00452 $0.00452
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00090 $0.00090

Measured 2d ago against content hash 43b16b4fdb7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poland 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidance

Poland is the canonical public source for an official-source-first skill system for life and administration in Poland. Keep it useful to ordinary agent users, portable across Codex, Claude Code, Cursor, pi, and compatible Agent Skills hosts, and safe for public collaboration.

Repository Role

  • This repository owns the editable plugin source and releases.
  • Public metadata, installation, support, and provenance must point only to this standalone repository. Private build environments may pin immutable revisions without becoming public dependencies.
  • Personal cases, documents, credentials, screenshots, and account data never belong in this repository.

Product Boundary

  • Use only non-identifying categories and public source IDs in plugin inputs.
  • Prefer the competent Polish authority or an official EU source, record access and verification dates, and preserve uncertainty and conflicts.
  • The plugin may inspect packaged data offline and probe allowlisted public pages without credentials. It bundles no Browser or Computer adapter, authenticated connector, credential store, or external-action executor.
  • Skill instructions may orchestrate a caller-owned Browser, Computer tool, or approved connector when that capability is installed and its own policy permits the task. If none is available, give semantic manual steps and stay with the user through each checkpoint.
  • Public research may be autonomous. Authentication, account selection, secret entry, CAPTCHA, and 2FA are user-only; pause capture and yield control before they begin. Resume only after the user says the protected session is ready.
  • After explicit task-scoped authorization, inspect only the personal records needed for the named task and fill only necessary, reviewable fields. Keep personal values out of the bundled CLI, MCP, receipts, tests, logs, and repo.
  • Obtain fresh action-time confirmation against a visible summary before any submit, send, booking change, payment initiation, upload, download, account or record change, or other consequential external effect. A broad instruction at task start is not confirmation for every later action.
  • Treat scenario and channel stop_before values as mandatory pause-and-classify checkpoints. Continue only when the concrete action is allowed and its scope or action-time checkpoint has completed; user-only and unresolved actions stop.
  • The user performs signatures, legal attestations, final payment authorization, irreversible destructive actions, and any step whose truth or legal effect only the user can accept. Never bypass controls, forge a declaration, obscure costs, or claim completion without a visible official receipt or final state.

Read the full file on GitHub · 86 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 · 86 lines · 905 tokens per session scan A 43b16b4fdb7b

Subscribe to this mod's changes

poland AGENTS.md is an instructions file published in the GitHub repository Xopoko/poland (0 stars, last pushed 6d ago), licensed MIT. It adds 905 tokens to every session, about $0.0045 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.

Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens