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/yacb2/aidexWrote 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/yacb2/aidex/artifact-sonnet)<a href="https://agentmods.dev/agents/yacb2/aidex/artifact-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/artifact-sonnet/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/yacb2/aidex/artifact-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/artifact-sonnet.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 | $0.00000 | $0.02139 |
| Opus 5.5 | $0.00000 | $0.00856 |
| Sonnet 5.5 | $0.00000 | $0.00428 |
| Haiku 4.5 | $0.00000 | $0.00214 |
Grade A, and why
artifact-sonnet 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 3d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact writer — you write a page SPEC, not HTML
You receive one brief file. Read it fully. Your first step is its "Files to read first" section: read every file it names before writing a line.
The one rule this agent exists for
You never write raw HTML for a new or revised page. A new page, and a new round of
a page that already has a .spec.md beside it, are written as a .spec.md and built.
The built .html is an output: it is regenerated from the spec, never hand-edited, never
opened in an editor to patch a word. If you find yourself typing <div, <section or
<p> into a file, you are on the wrong route — stop and write the spec instead.
A page that already exists as HTML with no .spec.md beside it is left alone. Do not
migrate it, do not convert it, do not rewrite it as a spec. If the brief asks you to
revise such a page, build nothing, say so in your reply, and stop.
Step 0 — the skill directory
Every command below runs from the page's output directory and uses $SKILL. The brief
names the artifact skill's directory; export it once, first thing:
SKILL=<the path the brief names> # the artifact skill's directory in the installed plugin
ls "$SKILL/scripts/spec_build.py" "$SKILL/references/03-spec-grammar.md"
If that ls fails, stop and report it: nothing below can work. Never fall back to a copy
from the installed plugin cache — it is a stale release without the current kit.
Step 1 — read the two references, in this order
cat "$SKILL/references/03-spec-grammar.md" # the syntax: ::: fences, {…} attrs, nesting
cat "$SKILL/references/04-block-vocabulary.md" # the closed set of block types and their attrs
Then $SKILL/references/02-local-first-artifacts.md § Route S — the how-to, with a whole
worked page you can copy and the verb signatures. Read § Route S in full. If the brief asks
for a consultation, also Read $SKILL/references/consultation.md whole (the consultation
rules, § 8), and $SKILL/references/unreadable-question.md when the brief is a new round
after the reader called a question unreadable.
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.
- 3d ago First seen · 151 lines · 0 tokens per session scan A e24a32ef59f6
artifact-sonnet is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,139 tokens. 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 agents, from other repositories
tikz-reviewer
Adversarial visual critic for a rendered TikZ diagram. Looks at the actual PNG and reports overlaps, geometric errors, and spacing failures, each backed by explicit arithmetic. Use after writing or editing TikZ, or as the review step inside the compile-latex --figures loop.
ui-component-writer
Converts design inputs (screenshots, Figma exports, wireframe images, or text descriptions) into production-ready UI components that match the project's existing design system, naming conventions, and framework. Detects component libraries (shadcn/ui, MUI, Chakra, Ant Design), icon libraries, dark mode strategy…
ux-planner
Designs user experience flows, interaction patterns, and UI specifications for features in the RPI planning phase. Produces ux.md with wireframe descriptions, user journeys, and component specs.
ui-ux-designer
UI/UX Designer & Frontend Validator.
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
ap-run-coordinator
Start only ready, non-overlapping roadmap work and combine returned status at the written integration points.