poland-protection-referral

poland-protection-referral is a skill for Claude Code, Codex from Xopoko/poland. It costs 29 tokens per session (955 once invoked), scanned A, original, MIT.

A safety-focused guide to official referral routes for asylum, international or temporary protection, unsafe return, or loss of protection in Poland.

In plain words
What is it for?
It helps classify the protection route, check official decisions and deadlines, distinguish UKR-status transition from CUKR procedures, and find the correct official next step.
Why use it?
It helps identify urgent risks such as detention, removal, coercion, or deadlines and directs the person to the appropriate authority without offering asylum strategy or judging credibility.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the poland plugin — 33 skills, 1 MCP server shipped together

Good fit It helps classify the protection route, check official decisions and deadlines, distinguish UKR-status transition from CUKR procedures, and find the correct official next step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xopoko/poland/poland-protection-referral
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.

Any agent
npx skills add Xopoko/poland --skill poland-protection-referral
Clone the repo
git clone --depth 1 https://github.com/Xopoko/poland

Made for: Claude Code, Codex.

Or install poland, the plugin that ships this one along with the rest of its 33 skills, 1 MCP server.

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.

agentmods badge for poland-protection-referral

README.md
[![agentmods](https://agentmods.dev/badge/skills/xopoko/poland/poland-protection-referral/github.svg)](https://agentmods.dev/skills/xopoko/poland/poland-protection-referral)
Your own site
<a href="https://agentmods.dev/skills/xopoko/poland/poland-protection-referral"><img src="https://agentmods.dev/badge/skills/xopoko/poland/poland-protection-referral/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.

agentmods 80×15 button for poland-protection-referral

Your own site · 80×15
<a href="https://agentmods.dev/skills/xopoko/poland/poland-protection-referral"><img src="https://agentmods.dev/badge/skills/xopoko/poland/poland-protection-referral.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 955 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00955
Opus 5 $0.00015 $0.00477
Sonnet 5 $0.00006 $0.00191
Haiku 4.5 $0.00003 $0.00096

Measured 11d ago against content hash 0cf48477b8b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

poland-protection-referral 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 11d 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.

skills/poland-protection-referral/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Poland Protection Referral

Use for international protection, temporary protection, unsafe return, loss of protection, or uncertainty about the competent protection authority. This skill provides official-source referral and safety-oriented next steps, not asylum strategy or a credibility assessment.

First check for immediate danger, detention, removal, coercion, or an imminent deadline. Route urgent safety needs to poland-emergency-rights without delaying for documents or immigration intake. Otherwise ask only for non-identifying route categories such as current country, stated status, protection type if known, locality, and whether an official decision or deadline exists.

For a reported PESEL UKR or CUKR matter, classify these as separate routes:

  • udsc-ukraine-status-transition-2026 owns the general 5 March 2026 transition. It does not make every extension or exception applicable to every Ukrainian citizen or every UKR-status holder.
  • udsc-cukr-procedure owns the CUKR route. At the 28 August 2026 source snapshot, the page says the electronic MOS procedure opened on 4 May 2026 and gives a current filing window ending 4 March 2027. Recheck the page before action and verify the source-defined applicant group, active-status dates, continuity, child branch, pending-case interaction, voivode, and current consequences. Never decide eligibility from the label PESEL UKR alone.
  • udsc-pesel-ukr-passport-update-2026 is the competent UdSC notice for the declaration-based 31 August identity-confirmation group. The broader gov-pesel-ukr-passport-update-2026 outreach notice also names new or changed passports and children whose registration lacked a passport. The two pages differ in affected-group scope and in the certainty of the stated status consequence; preserve the route's explicit conflict gate instead of choosing one formulation. Use sejm-ukraine-transition-act-2026 to classify the deadline: Article 25 sets 31 August 2026 for identity confirmation when PESEL was assigned on the basis of a declaration, while Article 26 gives specified other original-document situations a separate 60-day period from travel-document issuance. Do not present either rule as a universal deadline for every PESEL UKR holder. Verify the original registration basis, whether identity was already confirmed, and current gmina or city-office instructions; treat a near deadline or unclear record as an escalation.

Do not merge the 31 August PESEL-record deadline with the CUKR application window. Ordinary PESEL administration belongs to poland-identity after the time-sensitive UKR-status branch has been classified.

Use current Office for Foreigners and other competent official or support sources returned by the registry. Distinguish official observation, user-reported fact, and unresolved legal judgment. Give the authority, source, questions to ask, deadline-preservation step, and qualified legal-aid route. Do not predict an outcome, assess evidence credibility, or prepare a personalized protection claim.

If the user requests portal or correspondence assistance, apply ../../references/automation-playbook.md without delaying immediate safety or legal-aid referral. The user authenticates, signs, and attests to the truth of a protection account. For CUKR, a caller-owned tool may resume after the user's authentication to inspect only the explicitly scoped record and prepare administrative fields. Account creation, server-side draft creation, upload, download, payment initiation, booking, or submission requires fresh action-time confirmation; the user personally performs every signature and declaration. For a PESEL UKR passport-data update, the agent may locate the competent gmina, prepare a checklist, and prepare an appointment with confirmation, but the user personally presents identity documents and authorizes any official-record change. Do not turn operational assistance into a credibility assessment or individualized asylum strategy, and report completion only from a visible official receipt or confirmed office result.

Read the full file on GitHub · 76 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 76 lines · 29 tokens per session scan A 0cf48477b8b6

Subscribe to this mod's changes

poland-protection-referral is a skill published in the GitHub repository Xopoko/poland (0 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 955 once invoked, about $0.0001 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 skills, from other repositories

yuwen-publish-precheck

A Chinese-language review workflow for checking content before publishing it on Douyin, Xiaohongshu, or WeChat Channels.

yuwen-cool/yuwen-publish-precheck · 206 tokens

lov-china-website-filing

A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.

lovstudio/skills · 75 tokens

telnyx-email-suppressions-curl

Manage email suppressions (blocks), import and export suppression lists, and manage unsubscribe groups. Use for deliverability compliance and bounce handling.

team-telnyx/ai · 37 tokens

healthcare-providers-verify

Validates practitioner credentials and license status against the NPI registry. Cross-references specialties, credentials, and practice addresses against official records. Returns Verified / Partially Verified / Unverified / Flagged per practitioner with mismatch details and source URLs. Triggers: "verify these…

Nimbleway/agent-skills · 186 tokens

python-packaging-license-finder

Use this skill to deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using shallow cloning.

opendatahub-io/ai-helpers · 38 tokens

lov-public-security-filing

A guided workflow for applying for Chinese public-security internet filing after a website has passed ICP filing and is publicly accessible in mainland China. ICP filing is the earlier Chinese registration required for many mainland websites; public-security filing is a separate police-record process.

lovstudio/skills · 66 tokens