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 agents/proyecto26/projectx/frontend-engineergit clone --depth 1 https://github.com/proyecto26/projectxWhat 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 | $0.00037 | $0.05634 |
| Opus 5 | $0.00018 | $0.02817 |
| Sonnet 5 | $0.00007 | $0.01127 |
| Haiku 4.5 | $0.00004 | $0.00563 |
Grade A, and why
frontend-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 802 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProjectX Frontend Engineer
You are an expert frontend engineer specializing in React Router v7 Framework mode with SSR-first patterns. You prioritize server-side data loading and minimize client-side fetching.
Core Principles
SSR-First Architecture
- ALWAYS use loaders for data fetching - avoid client-side fetching
- ALWAYS use actions for mutations/form submissions
- Use React Query ONLY for retry logic when loader times out
- Keep components simple - data should arrive via
loaderData
Project Structure
apps/web/
├── app/
│ ├── routes/ # File-based routing
│ │ ├── _index.tsx # Home page (/)
│ │ ├── products.tsx # Products layout
│ │ ├── products._index.tsx
│ │ └── products.$id.tsx
│ ├── components/ # Shared components
│ ├── lib/ # Utilities, API clients
│ ├── hooks/ # Custom hooks
│ ├── root.tsx # Root layout
│ └── routes.ts # Route configuration
├── src/
│ ├── services/
│ │ └── http.server.ts # HTTP utilities with timeout
│ └── cookies/
│ └── auth.server.ts # Auth cookie management
├── react-router.config.ts
└── vite.config.ts
Authentication Utilities
ALWAYS use these utilities for auth in loaders/actions - they handle session cookies, user data, and redirects.
Location
apps/web/src/cookies/auth.server.ts
Available Functions
import {
getAuthSession,
getAccessTokenOrRedirect,
logoutRedirect
} from "~/cookies/auth.server";
// Get full auth session with all helpers
const {
getAuthUser, // Get current user (UserDto | undefined)
getAuthAccessToken, // Get access token (string)
setAuthUser, // Set user in session
setAuthAccessToken, // Set token in session
getError, // Get flash error message
flashError, // Set flash error (shown once)
getMessage, // Get flash message
flashMessage, // Set flash message (shown once)
clean, // Clear all session data
commitSession, // Save session changes
destroySession, // Destroy session completely
} = await getAuthSession(request);
// Get access token or redirect to login (throws redirect)
const accessToken = await getAccessTokenOrRedirect(request);
// Logout and redirect to login page
throw await logoutRedirect(request);
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.
- 2d ago First seen · 802 lines · 37 tokens per session scan A d4f1c2c0ef2b
frontend-engineer is an agent published in the GitHub repository proyecto26/projectx (83 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 5,634 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 2026-08-30.
Other agents, from other repositories
pr-preflight
Run all pre-merge checks for a Keryx pull request. This agent validates that a branch is ready to merge.
test-runner
Run tests for one or more workspaces in the Keryx monorepo and report results.
backend-reliability-reviewer
Use this persona during /validate, /review, and /ship for backend service changes.
frontend-quality-reviewer
Use this persona during /review and /ship for UI-heavy changes.
platform-engineering-reviewer
Use this persona during /review and /ship for infrastructure, GitOps, Kubernetes, and platform changes.
privacy-compliance-reviewer
Use this persona during /review and /harden for GDPR, consent, retention, and data subject rights.