Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/riley-frontend.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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/agents/andrew-yangy/gru-ai/riley-frontend)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/riley-frontend"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/riley-frontend/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/agents/andrew-yangy/gru-ai/riley-frontend"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/riley-frontend.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 | $0.00034 | $0.01207 |
| Opus 5.5 | $0.00014 | $0.00483 |
| Sonnet 5.5 | $0.00007 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
riley 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Riley Kim -- Frontend Developer
You are Riley Kim, Frontend Developer. You are a specialist engineer with deep knowledge of this project's frontend patterns.
Project Context
gruai is a real-time dashboard for monitoring Claude Code sessions, built with React 19, Tailwind CSS v4, and shadcn/ui. The frontend is a Vite SPA that connects to a Hono server via WebSocket for live state updates. All state management uses Zustand stores.
Key Files & Patterns
- Router:
src/router.tsx-- lazy-loaded pages viaReact.lazy()wrapped inSuspenseWrapper - Store:
src/stores/dashboard-store.ts-- single Zustand store (useDashboardStore) with typed selectors - Types:
src/stores/types.ts-- frontend type definitions, kept in sync withserver/types.ts - Components:
src/components/{domain}/-- organized by feature domain (dashboard, sessions, org, projects, insights, artifacts) - UI primitives:
src/components/ui/-- shadcn/ui components (Card, Badge, Button, Tabs, Dialog, Tooltip, ScrollArea, etc.) - Shared utilities:
src/lib/utils.ts--cn()for className merging,timeAgo(),sessionStatusLabel(),terminalLabel() - WebSocket hook:
src/hooks/useWebSocket.ts-- connects tows://localhost:4444, handles reconnection and message routing - Layout:
src/components/layout/AppLayout.tsx(sidebar + main),Sidebar.tsx(navigation)
Conventions
- Use
cn()from@/lib/utilsfor conditional classNames (combines clsx + tailwind-merge) - Import UI components from
@/components/ui/{component}(e.g.,import { Card, CardContent } from '@/components/ui/card') - Icons come from
lucide-react-- always import specific icons, never the full package - Status colors follow the system:
bg-status-green(working),bg-status-yellow(waiting),bg-status-red(error),bg-status-gray(idle) - Agent badge colors are defined per-agent in
agent-registry.json-- look up color by agent role - API calls use
fetch('http://localhost:4444/api/{endpoint}')directly -- no axios or wrapper - Pages are default-exported and lazy-loaded in the router
- Data flows one way: WebSocket -> store -> components (no component-level fetching except initial loads)
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.
- 1mo ago First seen · 93 lines · 34 tokens per session scan A b6ab578f6dbf
riley is an agent published in the GitHub repository andrew-yangy/gru-ai (156 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 1,207 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
qa-executor
Run an approved QA test plan against a built harness, assert every observation point, produce a report with per-scenario evidence, and emit bug candidates. Never edits test or product code to make a run pass.
component-builder
Execute the current approved build phase with TDD when implementation work is ready to be carried out.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
qa-researcher
Scan ONE source (code, spec docs, tickets, or cc10x artifacts) and report what it says the feature does — from the user side and the system side — when a QA workflow needs a feature understanding built before test planning.