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 cyanxxy/nl-tax-agent-skills --skill nl-tax-intakegit clone --depth 1 https://github.com/cyanxxy/nl-tax-agent-skillsWrote 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/cyanxxy/nl-tax-agent-skills/nl-tax-intake)<a href="https://agentmods.dev/skills/cyanxxy/nl-tax-agent-skills/nl-tax-intake"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-intake/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/cyanxxy/nl-tax-agent-skills/nl-tax-intake"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-intake.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 | $0.00046 | $0.02021 |
| Opus 5 | $0.00023 | $0.01010 |
| Sonnet 5 | $0.00009 | $0.00404 |
| Haiku 4.5 | $0.00005 | $0.00202 |
Grade A, and why
nl-tax-intake 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 12d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NL Tax Intake
Open a supported Dutch tax conversation and progressively build the taxpayer profile. This skill is conversational, not a fixed interview: credit facts and evidence already supplied, ask only the smallest useful follow-up, and let the conversation determine the order.
Always-on authenticated-portal boundary
Never use a browser, Claude in Chrome, computer use, screen interaction, a connector, or another tool to open or operate an authenticated tax portal; never log in, enter or change values, click controls, sign, send, submit, retrieve private account data, or ask for, accept, store, or process credentials or sessions. Those actions remain human-only even with taxpayer permission or available credentials. This boundary also applies on the informational fast path before any shared runtime resource is loaded.
Informational fast path — no intake state
Before reading or creating taxpayer/session files, decide whether the user is asking only for information. If they do not explicitly ask to prepare, organize, request, change, review, or stop a workpack:
- Do not create or update
profile.yaml,session-progress.yaml, workpacks, field maps, assumptions, or missing-info files. - Identify the supported year/topic and load only the directly relevant
source resource. For a 2026 provisional procedure question, use these exact
runtime paths instead of the raw reviewed portal-flow snapshots:
- request:
../nl-tax-provisional-assessment/reference/source-projections/request-flow-human.md - change:
../nl-tax-provisional-assessment/reference/source-projections/change-flow-human.md - stopzetten:
../nl-tax-provisional-assessment/reference/source-projections/stopzetten-flow-human.mdFor another topic, load only its directly relevant reviewed note under../_shared/knowledge/. Read the selected resource'ssource_ids, then search../_shared/source-register.yamlfor only those matching entries; do not read the complete register. Never open the raw reviewedrequest-flow.md,change-flow.md, orstopzetten-flow.mdin this fast path; their registeredsnapshot_pathvalues are maintainer provenance.
- request:
- Answer from the reviewed note and matched entries, not model memory. Keep annual and provisional rules distinct and state any manual-review or unsupported boundary in the note.
- Answer directly. A short offer to prepare later is fine, but do not ask screening questions unless the user then explicitly requests preparation.
What ships with it
6 files 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.
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.
- 12d ago First seen · 193 lines · 46 tokens per session scan A b22acd7ac3d7
nl-tax-intake is a skill published in the GitHub repository cyanxxy/nl-tax-agent-skills (10 stars, last pushed 17d ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,021 once invoked, about $0.0002 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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.