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-submit-companiongit 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-submit-companion)<a href="https://agentmods.dev/skills/cyanxxy/nl-tax-agent-skills/nl-tax-submit-companion"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-submit-companion/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-submit-companion"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-submit-companion.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 | $0.00041 | $0.01132 |
| Opus 5 | $0.00020 | $0.00566 |
| Sonnet 5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade C, and why
nl-tax-submit-companion scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
If the workpack or an applicable field map is incomplete, do not refuse. How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual-entry checklist
Create a Manual-entry checklist from an existing workpack and, where the workflow produces one, its field map. The taxpayer or an authorized representative performs every official action manually in Mijn Belastingdienst.
This skill is natural-language invocable only for explicit checklist intent. Run it when the user directly asks for the checklist or gives an unambiguous affirmative reply to the field mapper's immediately preceding checklist offer. Do not run it merely because a field map exists, and never require a slash command or magic phrase.
Read first
Resolve every workspace/... path against workspace_root from
session-progress.yaml (or profile.yaml); never create a second workspace/
tree. Read ../_shared/runtime-contract.md first. Resolve bundled files
relative to this skill directory with the host's skill-resource or file tools.
Do not depend on shell visibility or vendor-specific environment variables.
- The relevant workpack:
workspace/annual/2025/return-pack.mdorworkspace/provisional/2026/provisional-pack.md. - The matching
field-map.yamlis required for annual, provisional request, and provisional change. It is not expected forprovisional_2026_revieworprovisional_2026_stopzetten, so its absence is not a blocker for either workflow. - For
provisional_2026_review, readworkspace/provisional/2026/review-questions.md. If that review has already routed to a generated change workpack, use the change workpack and its field map instead. - The relevant submit-step reference (
reference/annual-submit-steps.md,reference/provisional-submit-steps.md, orreference/stopzetten-submit-steps.md). templates/manual-submission-checklist.md.workspace/shared/missing-info.mdandworkspace/shared/assumptions.md, if present.
Output order — blockers first, then steps
Write workspace/shared/manual-submission-checklist.md in this order:
- Blockers (first). Everything that must be resolved before the user opens Mijn Belastingdienst: unresolved
MISSING - enter manuallyrows and everymanual_review_requiredrow from an applicable field map; deferred items inmissing-info.md; unconfirmed assumptions; review questions marked open or change-needed; and — for a voorlopige aanslag change — the "prepare and verify the complete dataset; the change form requires all applicable categories, not only the changed item" reminder. If there are no blockers, say so explicitly. Never report a missing field map as a blocker for review or stopzetten. - Pre-flight. What to have ready: the evidence documents and the workpack open alongside the portal, plus the field map when that workflow produces one.
- Step-by-step entry or review. Use the ordered human steps from the relevant submit-step reference. Cross-reference values and source codes to field-map rows only for annual, provisional request, or provisional change. For review, use the review-question rows and route any change-needed item to the change flow; for stopzetten, use the stopzetten reference without inventing field-map rows.
- Final human review. The checks the taxpayer performs before deciding whether to sign and submit personally.
What ships with it
5 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 · 84 lines · 41 tokens per session scan C 4e03abf76949
nl-tax-submit-companion 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 41 tokens to every session and 1,132 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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.