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 agentmods add skills/mui/material-ui/material-ui-reviewnpx skills add mui/material-ui --skill material-ui-reviewgit clone --depth 1 https://github.com/mui/material-uiWrote 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/mui/material-ui/material-ui-review)<a href="https://agentmods.dev/skills/mui/material-ui/material-ui-review"><img src="https://agentmods.dev/badge/skills/mui/material-ui/material-ui-review.svg" alt="Measured on agentmods" 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 | $0.00137 | $0.04826 |
| Opus 5 | $0.00068 | $0.02413 |
| Sonnet 5 | $0.00027 | $0.00965 |
| Haiku 4.5 | $0.00014 | $0.00483 |
Grade A, and why
material-ui-review 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material UI Review
Review current diff. Find regressions and correctness bugs first. Also find
cleanup (reuse / simplification / efficiency). Default effort: medium. See
Effort levels for depth and subagent fan-out.
Argument hint: [low|medium|high|xhigh|max] [--fix] [--comment [inline]] [<target>]
This skill is opt-in only: run it when the user explicitly asks for it by
name (/material-ui-review, $material-ui-review, "the Material UI review skill", or a CI
job configured to use it). A plain "review my changes" or "review this PR", or
wrapping up an implementation, is not an invocation — review without this
workflow unless the user names it.
medium = precision. Every finding actionable. high, xhigh, max =
recall. Missed bug ships. Keep uncertain findings when mechanism is real;
label them clearly.
Scope
Local review: diff branch against upstream
(git diff @{upstream}...HEAD, fall back to main / master, or HEAD~1).
Fold in uncommitted + untracked changes — review often runs pre-commit. If PR link,
branch name, or file path passed as argument, review that target instead.
Effort levels
- low — bugs only. Flag runtime-correctness bugs and regressions. Skip Tests, Simplifications, Docs, and test/fixture hunks. No subagents. Precision bias.
- medium (default) — main agent reviews Bugs, Tests, Simplifications, Docs, and triggered API/performance concerns. Main agent verifies candidates. Large, risky, fragile, shared, or cross-component diff? Add exactly one adversarial bug hunter agent. Small, low-risk, isolated diff? No subagent. Precision bias.
- high — spawn 3 independent subagents: bugs/regressions, test gaps, simplifications. Main agent reviews the whole diff, including bugs, docs, and triggered API/performance concerns. Main agent dedups and sanity-checks. Large, risky, fragile, shared, or cross-component diff? Add exactly one adversarial bug hunter agent. No verifiers. No final sweep.
- xhigh —
highplus a docs subagent and one fresh missed-bug sweep. Fan out adversarial bug hunters across the highest-risk affected code regions (modules/components — not the four review areas). Max 2 adversarial bug hunters total, including the hunter inherited fromhigh. Other role subagents do not count toward this cap. No verifiers. Recall bias. - max —
xhighplus an independent verifier for every surviving candidate. Cover every affected code region across max 6 adversarial bug hunters total, including hunters inherited fromxhigh; other role and verifier subagents do not count toward this cap. When there are more than 6 regions, give the highest-risk regions dedicated hunters and group related remaining regions into shared assignments. Prioritize public runtime code, shared utilities, cross-component invariants, and fragile state/timing boundaries. Maximum recall.
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.
- 3d ago First seen · 442 lines · 137 tokens per session scan A da78e08a679e
material-ui-review is a skill published in the GitHub repository mui/material-ui (98,975 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 4,826 once invoked, about $0.0007 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
find-release
A skill to find the lowest Dart and Flutter release containing a given commit. Use this skill whenever users ask about when a commit landed in Flutter or Dart releases, inquire about release versions for specific SHAs, or want to know if a commit is included in stable, beta, or dev channels for Flutter/Dart projects.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
create-component
End-to-end SEED component implementation guide for React Web, Lynx, and cross-platform work. Use when adding or changing components across rootage, qvism, react/lynx packages, registry snippets, docs, examples, or when writing/refactoring docs/stories Storybook files. Story-only work follows a CSF Next fast path…
snapshot-release
Drives the snapshot-release flow for the current branch's PR. Posts a /snapshot comment on the PR if one isn't already there (with confirmation), waits for the Continuous Releases workflow to finish, and reports the tarball URLs from the resulting 📦 Snapshot Release comment. Use for both triggering and waiting …
migrate
Migrate a component or directive to Angular 22+ signal-based patterns.