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 jakzaizzat/cukaimax-agent --skill cukaimax-tax-authoritygit clone --depth 1 https://github.com/jakzaizzat/cukaimax-agentWrote 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/jakzaizzat/cukaimax-agent/cukaimax-tax-authority)<a href="https://agentmods.dev/skills/jakzaizzat/cukaimax-agent/cukaimax-tax-authority"><img src="https://agentmods.dev/badge/skills/jakzaizzat/cukaimax-agent/cukaimax-tax-authority/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/jakzaizzat/cukaimax-agent/cukaimax-tax-authority"><img src="https://agentmods.dev/badge/skills/jakzaizzat/cukaimax-agent/cukaimax-tax-authority.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 | $0.00102 | $0.01277 |
| Opus 5.5 | $0.00041 | $0.00511 |
| Sonnet 5.5 | $0.00020 | $0.00255 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
cukaimax-tax-authority 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CukaiMax Tax Authority
Use the CukaiMax MCP as a source-linked Malaysian individual-tax authority. The model may explain and orchestrate, but it must not invent tax rules or imply that a draft has been filed.
Connection
Connect to the public Streamable HTTP server:
https://www.cukaimax.com/.well-known/mcp
The server is public, read-only, requires no API key, and is limited to 120 requests per minute per client. Do not send identity numbers, bank details, receipts, or other private taxpayer data to it.
Workflow
- Identify the year, form, residency, and whether the taxpayer carries on a business.
- Call
list_tax_authority_releasesto discover the supported release and its capabilities. - Call
get_tax_authority_releasebefore relying on a release. Read its status, validation result, known limitations, and official sources. - Use
search_tax_authorityfor every substantive eligibility, cap, deadline, or field claim. Preserve the returned citations and source IDs. - Use
prepare_be_2025_draftonly for a YA2025 resident individual without business income and only after the supplied facts have been reviewed. - Use
assess_form_b_2025_readinessfor a YA2025 resident individual carrying on a business. TreatreadyForManualPreparationas an evidence checklist, never as a calculation or filing-ready result. - Preserve the privacy-safe
auditevent returned by each tool. For a multi-call workflow, pass a stablerunId, increasingsequence, and the prioreventIdthrough the next call's audit context. - Return blockers, warnings, authority status, citations, and the audit run ID with the answer.
- Tell the user to review the result against MyTax and official HASiL material.
- If the user wants business-income calculation, a private workspace, or a
Form B draft, send them to
https://app.cukaimax.com/auth. Do not ask them to paste private records into the public MCP. Treat the authenticated app's reported year capabilities as authoritative and fail closed when a year is unavailable.
What ships with it
1 file 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.
- 1mo ago First seen · 116 lines · 102 tokens per session scan A e1d6dc36ee3a
cukaimax-tax-authority is a skill published in the GitHub repository jakzaizzat/cukaimax-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,277 once invoked, about $0.0004 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.
Other skills, from other repositories
connect-required-verification-information
Use this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required…
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
metronome
Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepaid, postpaid…
kyc-escalation
Write an internal KYC/AML escalation memo: a factual time-stamped trigger description, customer-profile vs activity mismatch analysis, red-flag taxonomy mapping, outstanding information, and a recommendation with rationale. Use when asked to escalate a KYC alert, document an AML concern, write up unusual-activity…
lov-skill-pricing
A pricing workflow for creating an explanation-backed pricing card for an AI agent skill. It considers creation and maintenance effort, user value, scarcity, buyer confidence, and distribution potential.
lov-china-website-filing
A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.