Borrowing it
Nothing to install: this file belongs to beliq-eu/beliq-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/beliq-eu/beliq-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/beliq-eu/beliq-mcpWrote 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.
[](https://agentmods.dev/instructions/beliq-eu/beliq-mcp/agents-md)<a href="https://agentmods.dev/instructions/beliq-eu/beliq-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/beliq-eu/beliq-mcp/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.
<a href="https://agentmods.dev/instructions/beliq-eu/beliq-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/beliq-eu/beliq-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01363 | $0.01363 |
| Opus 5.5 | $0.00545 | $0.00545 |
| Sonnet 5.5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
beliq-mcp 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent rules for the beliq connectors, SDKs and tools
This repo is one of the public beliq-eu repos that put the beliq e-invoice API in front of
users: the SDKs, the CLI, the MCP server, the GitHub Action, the connectors and shop plugins,
and the shared configuration in beliq-eu/.github. These rules bind every change in any of
them, whoever or whatever makes it.
The beliq promise
What beliq promises. For each e-invoice format, beliq checks a document against the highest standard that exists for that format, and shows what backs every verdict: the rule pack, its version and a badge for how deep the check goes.
What that asks of every change, in every repo.
- Every format, field, business rule, default and derived value traces to an official public source: CEN/TC 434, KoSIT, FNFE-MPE, OpenPeppol, OASIS, UN/CEFACT or the national tax authority. A blog post, a forum answer, a vendor paper or a competitor's behaviour is not a source.
- Where no source settles a value, stop and say so. Do not fill the gap with a plausible value, a rounding or a fallback. This binds what beliq generates, converts and parses as much as its verdicts.
- Claim only what the code does today, on every surface: API responses, docs, landing page, legal texts, emails, the support bot, connectors, and PR and commit text.
- Read versions, error codes, statuses and badges from their one source. Do not type a copy by hand.
The limits, which are part of the promise.
validmeans the document passed the rule packs and schemas listed for its format, in the stated versions. It does not mean every recipient, validation tool or tax authority accepts it.- The depth of the check differs by format, and the badge says which:
Authority-checked(the authority's own rules),Community-checked(real business rules from an independent pack, not the authority's own),Schema-checked(structure only, no business rules). Never show a verdict as deeper than its badge. - beliq is a format vendor, not a transmission operator.
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.
- 1mo ago First seen · 93 lines · 1,363 tokens per session scan A 1e1c2c08c347
beliq-mcp AGENTS.md is an instructions file published in the GitHub repository beliq-eu/beliq-mcp (0 stars, last pushed today), licensed MIT. It adds 1,363 tokens to every session, about $0.0055 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 2026-10-02.
beliq-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| beliq-mcp AGENTS.mdbeliq-eu/beliq-mcp | Instructions file | 0 | today | MIT | A | 1,363 | 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 | today | 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 |