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 rules/andr-ca/agentharness/code-review-uigit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00046 | $0.01132 |
| Opus 5 | $0.00023 | $0.00566 |
| Sonnet 5 | $0.00009 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
code-review-ui 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 yesterday.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — UI / Frontend Layer
Focus on accessibility, performance, and correctness at the rendering boundary.
Accessibility (WCAG AA)
- Missing
alttext on images — every<img>needs analtattribute. Decorative images usealt="". Neveralt="image"oralt="photo". - Interactive element is not keyboard-accessible — a
<div onClick>or<span onClick>is not focusable by default. Use<button>or addrole/tabIndexand keyboard event handlers. - Color contrast — text must meet 4.5:1 contrast ratio (3:1 for large text). Check with a contrast analyzer before approving color changes.
- Missing form labels — every
<input>needs a visible<label>oraria-label. Placeholder text is not a substitute. - Inaccessible error messages — form validation errors must be associated with the input (
aria-describedby) and announced to screen readers. - Focus management after state change — modals, dialogs, and popups must move focus to the new content on open and restore it on close.
- Missing ARIA role on custom widget — a custom dropdown, slider, or menu must declare its ARIA role and maintain ARIA state (
aria-expanded,aria-selected, etc.).
State Management
- Server state stored in client state — data fetched from an API stored in
useState/useReducer/Vuex instead of a server state cache (React Query, SWR, Apollo). Leads to stale reads and manual invalidation bugs. - Derived state stored explicitly —
const [fullName, setFullName] = useState(...)whenfullName = firstName + lastNameis derivable. Store the minimum, compute the rest. - State updated without immutability — mutating a React/Vue state object directly (
state.items.push(...)) instead of returning a new reference. Breaks change detection. - Global state for local data — adding to a global store (Redux, Zustand, Pinia) something only one component uses. Use
useState/ component-local state first. - Missing loading / error states — async data fetch with no handling of the pending or error case. The UI silently shows nothing or crashes.
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.
- yesterday First seen · 53 lines · 46 tokens per session scan A cc10af460b59
code-review-ui is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,132 once invoked, about $0.0002 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 cursor rules, from other repositories
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.