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/21st-dev/claude-code-plugin/21st-ui-reviewnpx skills add 21st-dev/claude-code-plugin --skill 21st-ui-reviewgit clone --depth 1 https://github.com/21st-dev/claude-code-pluginWhat 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 | $0.00103 | $0.00437 |
| Opus 5 | $0.00051 | $0.00218 |
| Sonnet 5 | $0.00021 | $0.00087 |
| Haiku 4.5 | $0.00010 | $0.00044 |
Grade A, and why
21st-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.
Copies of this mod
2 near-identical copies found in the catalogue:
- 21st-ui-review — 100% identical, 0 lines differ
- 21st-ui-review — 100% identical, 0 lines differ
What it actually says
Review UI with evidence
Separate deterministic defects from subjective design recommendations.
Workflow
-
Read
.21st/design.json, project instructions, and the relevant source. -
Run the deterministic review first:
21st review <path> 21st review <path> --json -
Inspect the actual component composition and runtime states. Validate claims against code rather than inferring behavior from names.
-
Group findings into:
- deterministic defects;
- design-system drift;
- accessibility and interaction defects;
- responsive risks;
- subjective product/design recommendations.
-
Prioritize by user impact and include exact file and line attribution.
-
Use
21st review <path> --fixonly for deterministic, low-ambiguity fixes. Never silently redesign, change brand identity, or alter product behavior. -
Run relevant project tests after fixes and rerun review to prove resolution.
Review priorities
- semantic controls and accessible names;
- keyboard access, focus visibility, and dialog/menu behavior;
- image alternatives and meaningful labels;
- touch target size and disabled/loading states;
- responsive overflow and fixed-width assumptions;
- reduced-motion handling;
- hardcoded visual values that conflict with project tokens;
- duplicate primitives instead of existing components;
- inconsistent typography, radius, spacing, shadows, and icons;
- fake data, placeholder copy, or missing empty/error states.
Output
Lead with actionable findings ordered by severity. Keep subjective suggestions clearly labeled. If no issue is proven, say so and state what was inspected.
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 · 50 lines · 103 tokens per session scan A 78939e830bce
21st-ui-review is a skill published in the GitHub repository 21st-dev/claude-code-plugin (7 stars, last pushed 7d ago), licensed Apache-2.0. It adds 103 tokens to every session and 437 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…