Borrowing it
Nothing to install: this file belongs to KrzysztofMarmol/fakturownia-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/KrzysztofMarmol/fakturownia-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/KrzysztofMarmol/fakturownia-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/krzysztofmarmol/fakturownia-mcp/claude-md)<a href="https://agentmods.dev/instructions/krzysztofmarmol/fakturownia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/krzysztofmarmol/fakturownia-mcp/claude-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/krzysztofmarmol/fakturownia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/krzysztofmarmol/fakturownia-mcp/claude-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 | $0.01393 | $0.01393 |
| Opus 5.5 | $0.00557 | $0.00557 |
| Sonnet 5.5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
fakturownia-mcp CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Setup requirement
Development needs a sibling checkout of fakturownia-client at
../fakturownia-client — [tool.uv.sources] wires it as an editable path
dependency. CI also has a test-published job that resolves the client from
PyPI (uv sync --no-sources); remember --no-sources on uv run there too.
Commands
uv sync --extra dev
uv run ruff check . && uv run ruff format --check .
uv run mypy
uv run pytest # offline; in-memory MCP sessions + MockTransport
uv run pytest tests/test_tools.py::test_create_invoice_executes_when_approved
FAKTUROWNIA_DOMAIN=... FAKTUROWNIA_API_TOKEN=... uv run fakturownia-mcp # run stdio server
uv build && uv build aliases/invoiceocean-mcp -o dist
CI (ci.yml) runs the dev matrix (3.10/3.12/3.13, --cov-fail-under=85) plus
the published-pair job.
Architecture
FastMCP stdio server on the mcp v1 SDK (pinned <2.0; v2 migration is a
known future task). server.py builds the FastMCP instance with agent-facing
instructions and a lifespan that closes the shared API client on shutdown.
config.py— env-driven singletonAsyncFakturowniaClientwith an ownership flag:aclose_client()only closes clients it created, so tests can inject viaset_client()without the lifespan killing their instance. Every env var works with bothFAKTUROWNIA_andINVOICEOCEAN_prefixes (_env()helper;FAKTUROWNIA_wins).tools/{invoices,clients,payments,products}.py— each exposesregister(mcp); called once fromserver.pyviatools.register_all.prompts.pyregisters the MCP prompts the same way.mcpb/— source of the.mcpbone-click bundle (manifest + dependency pyproject + entry shim); versions there must match__version__and the release publishes it as a GitHub release asset (bundlejob).approval.py— elicitation gate for every mutating tool. It checks the client's declared elicitation capability first (clear error when absent), and the dialog message must show the actual values being written (format_fields).FAKTUROWNIA_SKIP_CONFIRM=1bypasses.errors.py—api_call()wraps every client-library call and rephrases failures into agent-steeringToolErrors (e.g. 404 → "ids come from list_* tools, not document numbers").schemas.py— sharedAnnotatedparameter types (date pattern, page bounds, status Literal, per-entity*UpdateFieldsdocs) andfull_record(), which strips secret fields (token,view_url,panel_url,payment_url) from any full model dump.
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 · 103 lines · 1,393 tokens per session scan A dd14506353da
fakturownia-mcp CLAUDE.md is an instructions file published in the GitHub repository KrzysztofMarmol/fakturownia-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,393 tokens to every session, about $0.0056 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.
fakturownia-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fakturownia-mcp CLAUDE.mdKrzysztofMarmol/fakturownia-mcp | Instructions file | 0 | 2mo ago | MIT | A | 1,393 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |