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-annual-returngit 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-annual-return)<a href="https://agentmods.dev/skills/cyanxxy/nl-tax-agent-skills/nl-tax-annual-return"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-annual-return/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-annual-return"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-annual-return.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 | $0.00036 | $0.01702 |
| Opus 5 | $0.00018 | $0.00851 |
| Sonnet 5 | $0.00007 | $0.00340 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
nl-tax-annual-return 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NL Tax Annual Return
Prepare a local, source-traceable 2025 annual-return workpack for manual entry in Mijn Belastingdienst. The taxpayer or an authorized human performs every authenticated portal action. Do not use a browser, Claude in Chrome, computer use, screen interaction, a connector, or another tool to open or operate the portal; do not log in, enter or change values, click controls, sign, send, submit, retrieve private account data, ask for, accept, store, or process credentials or sessions, collect BSN, present a final calculation, or describe the workpack as official advice.
This is an agent-led conversation, not a fixed interview or tax-decision engine. Credit facts and evidence already supplied, ask the smallest useful follow-up, persist after every turn, and keep one owning agent as the sole writer and readiness authority.
Activation and paths
Read ../_shared/runtime-contract.md first. Resolve bundled resources relative
to this skill directory and every workspace/... path against the saved
workspace_root; never depend on vendor-specific environment variables or
create a second workspace tree.
Before the first user-facing reply on every turn, re-read:
workspace/taxpayer/profile.yamlworkspace/shared/session-progress.yamlworkspace/taxpayer/evidence-index.yaml, if it exists
Confirm workflow_candidate: annual_2025. If profile/session state is absent,
require intake to create it and return to nl-tax-intake; do not create or
reconstruct intake-owned state. If intake is complete, never restart it.
For a request covering both supported workflows, annual 2025 must still be the
only active candidate and owner; the profile may also show provisional 2026 as
requested with status queued. Do not load provisional resources or write
provisional artifacts before the completed annual handoff in Phase 10.
For a pre-1.4 progress file, apply the legacy migration in
../_shared/knowledge/methods/interactive-elicitation.md without changing
existing answers. Use the saved conversation ledger to resume; it records facts
and gaps but does not dictate question order.
What ships with it
19 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.
- agents/openai.yaml 393 B
- assets/icon.png 31 KB
- reference/annual-flow.md 7.1 KB
- reference/annual-output-contract.md 31 KB
- reference/phases/01-5-filing-status.md 4.9 KB
- reference/phases/01-preflight.md 12 KB
- reference/phases/02-income.md 5.3 KB
- reference/phases/02a-winst.md 13 KB
- reference/phases/03-own-home.md 4.4 KB
- reference/phases/03a-box2.md 2.6 KB
- reference/phases/04-box3.md 6.1 KB
- reference/phases/05-5-credits.md 4.8 KB
- reference/phases/05-deductions.md 5.2 KB
- reference/phases/06-partner.md 3.0 KB
- reference/phases/07-field-map.md 725 B
- reference/phases/08-missing-info.md 641 B
- reference/phases/09-review-questions.md 634 B
- reference/phases/10-assembly.md 7.1 KB
- templates/annual-return-pack.md 49 KB
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 · 160 lines · 36 tokens per session scan A 4c5767098ec3
nl-tax-annual-return 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 36 tokens to every session and 1,702 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
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
regulatory-analysis
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.