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 cuesoftinc/oss-engineering-standards --skill cuelabs-web-standardgit clone --depth 1 https://github.com/cuesoftinc/oss-engineering-standardsWrote 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/cuesoftinc/oss-engineering-standards/cuelabs-web-standard)<a href="https://agentmods.dev/skills/cuesoftinc/oss-engineering-standards/cuelabs-web-standard"><img src="https://agentmods.dev/badge/skills/cuesoftinc/oss-engineering-standards/cuelabs-web-standard/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/cuesoftinc/oss-engineering-standards/cuelabs-web-standard"><img src="https://agentmods.dev/badge/skills/cuesoftinc/oss-engineering-standards/cuelabs-web-standard.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 | $0.00063 | $0.00637 |
| Opus 5 | $0.00032 | $0.00318 |
| Sonnet 5 | $0.00013 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
cuelabs-web-standard 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 9d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CueLABS Web Standard
Implement the web surface from the product's current documentation and design artifacts. Preserve product character while enforcing shared engineering, accessibility, testing, and integration contracts.
Read the relevant references
- Read references/web-implementation.md for architecture, tokens, MVC boundaries, routes, TEST_MODE, mocks, testing, accessibility, and implementation rules.
- Read references/web-tooling.md for package scripts, linting, formatting, Vitest, Playwright, Tailwind, Next.js config, performance, SEO, and parity files.
- Read references/marketing-parity.md only when touching marketing navigation, footer, themes, public links, or shared CueLABS copy.
Workflow
- Inspect repository instructions,
.cuelabs/project.yaml, product docs, source, tests, and the referenced design artifact. - Confirm the web surface is
active. If it isplanned, stop at design or planning unless the user explicitly asks to begin implementation. - Determine the task layer:
- foundations and tokens;
- UI components;
- public marketing;
- dashboard/application routes;
- models/controllers/network boundaries;
- testing/tooling;
- accessibility/performance/SEO.
- Read only the references needed for those layers.
- Reuse existing product components and tokens. Do not replace product design with a generic component kit.
- Keep views render-only, controllers responsible for orchestration, and models/repositories responsible for network access.
- Keep TEST_MODE behavior behind the standard provider and mock seams. Do not introduce production authentication merely to satisfy a web-only phase.
- Add or update unit, integration, and Playwright coverage for changed behavior.
- Verify with the repository's lint, typecheck, unit, build, and relevant e2e commands. Compare rendered output to the current design source when visual fidelity is in scope.
What ships with it
5 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.
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.
- 9d ago First seen · 69 lines · 63 tokens per session scan A 0c4afc74d8a9
cuelabs-web-standard is a skill published in the GitHub repository cuesoftinc/oss-engineering-standards (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 637 once invoked, about $0.0003 per session on Opus 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
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
industrial-brutalist-ui
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.