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 x1wealth/x1-agent-skills --skill ask-household-recordgit clone --depth 1 https://github.com/x1wealth/x1-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/x1wealth/x1-agent-skills/ask-household-record)<a href="https://agentmods.dev/skills/x1wealth/x1-agent-skills/ask-household-record"><img src="https://agentmods.dev/badge/skills/x1wealth/x1-agent-skills/ask-household-record/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/x1wealth/x1-agent-skills/ask-household-record"><img src="https://agentmods.dev/badge/skills/x1wealth/x1-agent-skills/ask-household-record.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 | $0.00109 | $0.01147 |
| Opus 5.5 | $0.00044 | $0.00459 |
| Sonnet 5.5 | $0.00022 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00115 |
Grade A, and why
ask-household-record 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This portable skill uses the live X1 MCP connection supplied by the host. It contains no X1 server implementation, credentials, or household data.
Ask the household record
Use this when a person wants to understand their own household structure or what one of their documents says. The useful result is one answer they can check: the fact, the document and page it came from, and the next question worth asking. X1 builds the record one real document at a time, and each fact the person confirms is there the next time they ask.
Start from what is already there
- Use only tools mounted on this connection. A tool named here may be unavailable; an absent tool is unavailable, and this skill grants no access or approval. When unsure what this account can do, read
get_user_capabilities. - Call
get_vault_documentsfirst to see whether the person already has a document that fits their question. If one exists, use it. Do not ask them to upload something X1 already holds. - If nothing fits, ask for one real document: an operating agreement, a trust, a K-1, or an insurance policy. One document is enough to start.
Getting a new document in
Follow the mounted path exactly and report the state X1 returns.
- When
request_human_confirmationandrequest_vault_upload_linkare mounted, proposerequest_vault_upload_linkfor the person's own vault. The proposal uploads nothing; the person approves it in X1. Check it withget_my_action_requests, never retry a consumed request, and have the person finish the drop in X1. - Otherwise, send them to https://app.x1wealth.com/documents/vault to add it.
- After a deposit, use
check_vault_depositto confirm it arrived. Do not call a document searchable until X1 says so. Only when X1 says it is still reading a just-added document, ask the person to check back shortly.
Answer from the documents
- For what a document says (a trustee, a member's share, a tax election, a distribution clause), use
search_my_document_contents. It returns quoted passages with the document and page. Answer only from those passages. - For what the person has already confirmed about their household, use
ask_household_brain. It answers from confirmed facts or declines. A decline is an answer, not a failure: say what is missing and which document would settle it. - For who owns what and which entity a document belongs to, use
list_household_entitiesandlist_household_entity_change_proposals.
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 · 67 lines · 109 tokens per session scan A c3e00d546487
ask-household-record is a skill published in the GitHub repository x1wealth/x1-agent-skills (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,147 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 2026-09-23.
Other skills, from other repositories
data-policy
Use when building internal data-governance machinery: a retention schedule (period, lawful basis, expiry action, system where deletion runs), an Art. 6 lawful-basis register, an Art. 30 ROPA, or a consent capture/withdrawal model. NOT the public privacy notice or DSAR handling (that is gdpr-privacy), NOT SOC 2 posture…
generate-fillable-contract-html
A generator for Chinese HTML templates with fill-in fields for contracts, quotations, and authorization letters. The fields are marked so a later HTML-to-Word conversion can identify and fill them.
docuseal-cli
Manage DocuSeal e-signature workflows from the terminal via the DocuSeal CLI - create templates from PDF/DOCX/HTML, send documents for signing, track submissions, and update submitters. Use when the user wants to run DocuSeal commands in the shell, scripts, or CI/CD pipelines. Always load this skill before running…
pii-redaction
Redact or remove PII (SSNs, EINs, names, addresses, phones, emails, account numbers) from documents while keeping the file in its original format and style. Use when asked to redact, mask, anonymize, scrub, sanitize, or de-identify a document.
bailii-case-download
Search BAILII (www.bailii.org) for a UK or Irish case and download the full judgment as a clean PDF. Use whenever the user wants a case from BAILII, gives a neutral citation (e.g. "[2024] EAT 114", "[2021] UKSC 5") or a BAILII URL and asks to fetch/download/save it, asks for "the full case as a PDF", wants to verify a…
legal-document-restoration
A tool for restoring an original legal document from an externally reviewed redacted DOCX file using a separate mapping file that records each replacement.