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-evidence-indexergit 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-evidence-indexer)<a href="https://agentmods.dev/skills/cyanxxy/nl-tax-agent-skills/nl-tax-evidence-indexer"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-evidence-indexer/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-evidence-indexer"><img src="https://agentmods.dev/badge/skills/cyanxxy/nl-tax-agent-skills/nl-tax-evidence-indexer.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 | $0.00029 | $0.01141 |
| Opus 5 | $0.00015 | $0.00571 |
| Sonnet 5 | $0.00006 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
nl-tax-evidence-indexer 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NL Tax Evidence Indexer
Organize the evidence the user actually supplies—selected files, host attachments, and values stated in chat—without requiring a complete document folder. Keep the interaction conversational and ask only for evidence that matters to the active annual or provisional workflow.
Activation
Use this skill when the user asks to index or organize Dutch tax evidence, when an active workflow needs evidence for a section, or when selected files or chat amounts need source-traceable recording. Credit everything already supplied; do not restart intake or turn the exchange into a fixed upload checklist.
Read before acting
Resolve bundled paths relative to this skill directory and every workspace/...
path against the saved workspace_root.
- Read
../_shared/runtime-contract.mdfirst. - Read
../_shared/knowledge/methods/interactive-elicitation.mdfor the shared conversational and session-state contract. - Read reference/indexing-flow.md whenever this skill is active; it owns the attachment, indexing, provenance, and update procedure.
- Read reference/evidence-types.md before
assigning a canonical
evidence_type, such aswoz_beschikking,hypotheek_jaaroverzicht, orvoorlopige_aanslag_beschikking. - Read reference/extraction-boundaries.md before classifying or extracting document facts.
- Read
workspace/shared/session-progress.yamland the existingworkspace/taxpayer/evidence-index.yaml. If the index does not exist, seed it fromtemplates/evidence-index.yaml.
Keep resource loading, file maintenance, and orchestration invisible to the user unless a specific evidence item needs review.
Core contract
- Accept a user-selected folder, selected host attachments, values stated in chat, or any combination of these. Never require a file when the active workflow permits a chat value.
- Inventory only the locations the user selected. The optional Python helper catalogs file metadata and hashes; it does not classify documents, extract tax facts, or choose tax treatment.
- Assign evidence types and confidence conversationally from the document and the reviewed references. Do not use a deterministic tax-classification or decision engine, compute tax, decide deductibility, or choose a partner allocation.
- Preserve provenance. A file stays
source: file; a value stated in chat usessource: user_chat, its verbatimquote, andstated_at; a deferred fact usessource: unknownand remains open. - Return chat answers to the active workflow for its profile or section notes.
An evidence-index chat row is only a resume-compatible record when the
indexer was already active. Do not invoke this indexer solely to turn chat
into document evidence; pure chat collection does not require an
evidence-index.yamlentry. - Never silently choose between conflicting file and chat values or between competing documents. Mark the item for review, describe the conflict, and ask the user which value or document should control.
- Ask at most three closely related evidence questions in one turn. Defer an
unavailable item to
missing-info.mdand continue with another useful item.
What ships with it
8 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 · 114 lines · 29 tokens per session scan A 70d2f8547d1a
nl-tax-evidence-indexer 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 29 tokens to every session and 1,141 once invoked, about $0.0001 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…