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.
npx skills add joosthel/sevdesk-mcp --skill sevdesk-bookkeepinggit clone --depth 1 https://github.com/joosthel/sevdesk-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/skills/joosthel/sevdesk-mcp/sevdesk-bookkeeping)<a href="https://agentmods.dev/skills/joosthel/sevdesk-mcp/sevdesk-bookkeeping"><img src="https://agentmods.dev/badge/skills/joosthel/sevdesk-mcp/sevdesk-bookkeeping/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/skills/joosthel/sevdesk-mcp/sevdesk-bookkeeping"><img src="https://agentmods.dev/badge/skills/joosthel/sevdesk-mcp/sevdesk-bookkeeping.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 | $0.00053 | $0.01123 |
| Opus 5.5 | $0.00021 | $0.00449 |
| Sonnet 5.5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
sevdesk-bookkeeping 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 17d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sevDesk bookkeeping workflows
Procedural knowledge for driving the sevdesk-mcp server well. The
server's own guardrails (drafts-only writes, read-only mode, dryRun)
hold regardless of this skill — this file is about doing the work in the
right order with few tokens, not about safety.
Orientation (once per session)
sevdesk_ping— verifies the token and returns two facts that change how you should work:mode: READ-ONLY / DRY-RUN / read-write.bookkeepingSystemVersion: 1.0 books withtaxType, 2.0 withtaxRule. Old documents may carry either; the tools decode both.
- The server never guesses a tax rule:
sevdesk_create_invoiceandsevdesk_create_voucherrequiretaxRuleId. Ask the user which treatment applies (regular VAT, §19 UStG, reverse charge…), and for vouchers read the allowed rules fromsevdesk_receipt_guidance.
Monthly close
Run in this order; each step's output feeds the next conversation turn:
sevdesk_find_duplicatesfor the month — resolve duplicates first, they distort every later number.sevdesk_audit_vatwithfrom/tofor the month. Work findings by severity.sevdesk_reverse_charge_reportfor the month — give the user the §13b bases for the VAT return (deductible nets to zero but must be declared; rule 13 VAT is actually payable).sevdesk_diff_receipt_folderif a receipt directory is allowlisted — unbooked receipts and unmatched bookings.sevdesk_invoice_aging— open receivables, never-sent drafts.sevdesk_subscription_gaps— expected recurring costs that are missing (a missing AWS invoice surfaces here, not in the audits).
Receipt triage (new expense documents)
sevdesk_receipt_guidancefor the expense type — it returns the booking accounts and tax rules the account's own configuration allows.sevdesk_upload_voucher_filethensevdesk_create_voucherwithdryRun: truefirst; show the user the preview, then repeat without dryRun once confirmed.- Foreign supplier without VAT? Do the §13b check below before booking.
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.
- 17d ago Changed · -3 lines 8f7babc1f163
- 2mo ago First seen · 95 lines · 53 tokens per session scan A d7fcb08755bd
sevdesk-bookkeeping is a skill published in the GitHub repository joosthel/sevdesk-mcp (9 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,123 once invoked, about $0.0002 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.
sevdesk-bookkeeping compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sevdesk-bookkeepingjoosthel/sevdesk-mcp | Skill | 9 | 3d ago | MIT | A | 53 | Claude Code, Codex |
| agoragentic-transaction-assurancerhein1/agoragentic-integrations | Skill | 41 | 16d ago | MIT | A | 65 | Cursor |
| hive-queryhive-intel/hive-sdk | Skill | 20 | yesterday | MIT | A | 132 | Claude Code |
| hive-tool-discoveryhive-intel/hive-sdk | Skill | 20 | yesterday | MIT | A | 100 | Claude Code |
| irs-tax-calculatordma9527/irs-taxpayer-mcp | Skill | 13 | 2d ago | MIT | A | 0 | Claude Code, Codex |
| stripeKevin-Liu-01/Agent-Machines | Skill | 29 | 15d ago | MIT | A | 29 | Claude Code |
| lease-accountingGAJETOso/financeskills | Skill | 47 | 5d ago | MIT | A | 64 | Claude Code |