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 cognitedata/builder-skills --skill aura-reviewgit clone --depth 1 https://github.com/cognitedata/builder-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/cognitedata/builder-skills/aura-review)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/aura-review"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/aura-review/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/cognitedata/builder-skills/aura-review"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/aura-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 44 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 80 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00137 | $0.03027 |
| Opus 5 | $0.00068 | $0.01514 |
| Sonnet 5 | $0.00027 | $0.00605 |
| Haiku 4.5 | $0.00014 | $0.00303 |
Grade A, and why
aura-review scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
than `curl` (curl requests to them get denied). How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aura Review
An objective, code-level audit of Aura usage in a generated app: did the app use Aura where Aura applies, and did it use the Aura components it did reach for correctly?
This skill never asks the user anything. It is designed to run unattended — inside a CI job on a nightly schedule, or by hand — and to always finish with a report and a machine-readable stats file.
The one rule that matters more than any step below
Only flag something as wrong if it is already written down in either
DESIGN.md or the public Aura docs. If you notice something that feels wrong
but isn't documented anywhere, do not invent a rule to justify flagging it,
that isn't a fair test of an app built against documentation that never
mentioned the rule. Instead, note it as a suggestion for the docs and move
on. This matters because these reports get used to tell people "Aura says
you did X wrong" — that claim has to be traceable to something they could
have read.
Likewise, when judging whether a custom component "could have been Aura",
only say so when you can point at a specific Use when bullet for a named
Aura component that matches — otherwise mark it undecided rather than guess.
Sources of truth (v1, Storybook is deliberately out of scope for now)
| Source | Location | Use it for |
|---|---|---|
DESIGN.md |
<app-dir>/node_modules/@cognite/aura/DESIGN.md |
Tokens, per-component "Use when" / "Use something else when" / "Dos and don'ts" / "Behavior", layout patterns |
| Aura docs site | https://docs.cognite.com/aura-design-system | Foundations (tokens, accessibility, design heuristics) and per-component Primitives pages for anything DESIGN.md doesn't cover — DESIGN.md's own "Docs reference" links here per component |
| Flows community components site | https://cognitedata.github.io/flows-community-components/ | Aura's public shadcn-style component registry and docs site — use for components or usage guidance not shipped in DESIGN.md |
What ships with it
1 file 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.
- 6d ago First seen · 245 lines · 137 tokens per session scan A 8b1c3c2c7340
aura-review is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 137 tokens to every session and 3,027 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
ss-lint
Quick automated lint — detects common design system violations in seconds.
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
ss-review
Review UI code for design system compliance, accessibility, and best practices.