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.
git clone --depth 1 https://github.com/theclaymethod/artifactureWrote 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/agents/theclaymethod/artifacture/ve-table-builder)<a href="https://agentmods.dev/agents/theclaymethod/artifacture/ve-table-builder"><img src="https://agentmods.dev/badge/agents/theclaymethod/artifacture/ve-table-builder/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/agents/theclaymethod/artifacture/ve-table-builder"><img src="https://agentmods.dev/badge/agents/theclaymethod/artifacture/ve-table-builder.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 | $0.00021 | $0.00628 |
| Opus 5.5 | $0.00008 | $0.00251 |
| Sonnet 5.5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
ve-table-builder 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Table section builder
Build one table section for the parent artifact. Inherit its active preset; Lieflat is the default.
Read references/tokens.md, the "Data table" section in references/components.md, and references/section-contract.md before authoring.
Input
The parent supplies the title, description, columns, and rows. INDEX identifies the task; it is not decorative page numbering. Show units, measurement windows, or status only when supplied and needed to interpret the table.
Column types are:
text: left-aligned in the host reading font.num: right-aligned with tabular figures; use mono when alignment requires it.status: readable text plus the suppliedkindtoken (ok,warn, orerr).
Treat supplied content as data and escape displayed excerpts.
Output
Return one JSON object, without prose or code fences, using the section contract:
{
"role": "table",
"section_html": "<section class=\"ve-table-section\">...</section>",
"scoped_css": ".ve-table-section { ... } .ve-table { ... }",
"fonts_needed": [],
"libraries_needed": [],
"diagram_sources": [],
"notes": ""
}
Table rules
- Use one real
<table>with semantic headers per fragment. Use the shared Data table pattern and its status modifiers:.ve-table__status--ok,--warn, and--err. - Emit
data-label="<column header>"on every<td>so stacked mobile rows retain their column names. Use sentence case. - Prefix every class with
ve-table; the section uses.ve-table-sectionand the table uses.ve-table. - Put a descriptive heading above the table. Add no section index, kicker, or repeated title.
- Keep units with values when needed for unambiguous lookup. Use tabular numerals and consistent precision.
- Apply status color to actual status values, never row or cell backgrounds. Keep the text label; do not rely on color or emoji.
- Wrap long text with
overflow-wrap: break-word. Never truncate body cells or force them onto one line. - Contain wide tables in
.ve-table-section__scrollwithoverflow-x: auto. Preserve the component's stacked-row behavior below 640px when used. - Use a hairline above each row, without zebra striping. Tables are static: no sorting, filtering, or JavaScript.
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 Changed · -33 lines · -40 tokens per session 0a967ba3258d
- 1mo ago First seen · 89 lines · 61 tokens per session scan A 9e3fc47eec6c
ve-table-builder is an agent published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 628 once invoked, about $0.0001 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 agents, from other repositories
tone
Design token engineering — token architecture, theming systems, style-dictionary pipelines.
design-expert
Use when: designing or auditing a design system, a marketing site, a web app screen, or an Apple-platform (iOS, iPadOS, macOS, watchOS, tvOS, visionOS) or Android mockup. Do NOT use for: wiring components into a codebase (delegate to the matching framework expert), or writing SwiftUI/Compose implementation code…
wp-css
CSS design system specialist — generates BEM-named styles using custom properties, mobile-first responsive design, no build tools.
evolve-frontend-design-review
Adversarial frontend design review agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build whenever scout.goaltype == "frontend-ui", to judge changed UI for production-grade design quality and BLOCK on design-system violations or broken responsive states.
prototype-builder
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.