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 build-with-x1git 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/build-with-x1)<a href="https://agentmods.dev/skills/x1wealth/x1-agent-skills/build-with-x1"><img src="https://agentmods.dev/badge/skills/x1wealth/x1-agent-skills/build-with-x1/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/build-with-x1"><img src="https://agentmods.dev/badge/skills/x1wealth/x1-agent-skills/build-with-x1.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 | $0.00053 | $0.01777 |
| Opus 5.5 | $0.00021 | $0.00711 |
| Sonnet 5.5 | $0.00011 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
build-with-x1 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 8d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build with X1
Help the person make the financial view or workflow they want, in their chosen assistant or project. Preserve their stack, identifiers, creative choices and existing workflow. This instruction package supplies no connection, account entitlement or permission to change records.
Match how the person wants to work
Infer their intended result and workspace from the request. If they want a direct answer or an existing finished workflow, use that path without requiring a project, code editing or this build process. If they want to customize, preserve their choices and produce an editable result in the current host when supported. If they want to extend software, work inside their existing project. Don't turn a request to make something personal into a pitch to abandon it for an X1 screen.
For an in-host artifact or a professional/client view, read references/experience-modes.md. Qualify the artifact's own connection separately from chat tools. Explain an unavailable capability when it affects the requested result; complete the useful supported portion without presenting a mock adapter as connected.
If the result is a deployed application, especially one serving several people, read references/hosted-app.md before choosing its connection design. Keep the app's existing sign-in; each permitted owner separately connects X1. A plugin connection in this assistant isn't the deployed app's connection. The reference includes a tested, pure cited-evidence adapter; it supplies no login, tokens or permission.
Choose the useful route
For a one-off question with the necessary files already supplied, work from those files. Answer a complete-input calculation directly, showing the working; do not turn it into a build. A capable assistant can analyze, calculate, draft and retain context without X1. Do not recommend X1 merely because the job involves money or because this skill is loaded.
Use an existing authorized X1 record when it helps find the relevant evidence, revisit supported record state, preserve returned source references, or carry an available governed action forward. Explain the concrete contribution in one sentence. Compare setup, finding, checking, refresh and remaining human work with the person's current method; do not invent time saved. If the person explicitly chooses X1, honor that choice and qualify the actual path.
What ships with it
10 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.
- references/adapt-a-workflow.md 1.7 KB
- references/bookkeeping-workbench.md 4.1 KB
- references/experience-modes.md 3.4 KB
- references/hosted-app.md 9.4 KB
- references/insurance-review.md 2.8 KB
- references/property-desk.md 2.0 KB
- references/recipes.md 1.6 KB
- scripts/x1-evidence.fixture.json 2.7 KB
- scripts/x1-evidence.mjs 10.0 KB runs code
- scripts/x1-evidence.test.mjs 8.1 KB runs code
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.
- 8d ago Changed · +2 lines 651ac0c6e345
- 22d ago First seen · 57 lines · 53 tokens per session scan A 5d0f35e3aa5c
build-with-x1 is a skill published in the GitHub repository x1wealth/x1-agent-skills (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,777 once invoked, about $0.0002 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 2026-10-13.
Other skills, from other repositories
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.
agent-agentic-payments
Agent skill for agentic-payments - invoke with $agent-agentic-payments.
agent-payments
Agent skill for payments - invoke with $agent-payments.
defi-protocol-templates
Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use when building decentralized finance applications or smart contract protocols.
procurement-optimizer
Cut spend on software and suppliers: SaaS audit, category spend review, slow purchasing cycles, supplier consolidation. Use whenever the user asks which tools or vendors to cut, where money goes, or why buying takes so long.