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/ljojua1998/skills/frontend-developergit clone --depth 1 https://github.com/ljojua1998/skillsWrote 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/ljojua1998/skills/frontend-developer)<a href="https://agentmods.dev/agents/ljojua1998/skills/frontend-developer"><img src="https://agentmods.dev/badge/agents/ljojua1998/skills/frontend-developer.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 | $0.00044 | $0.00988 |
| Opus 5 | $0.00022 | $0.00494 |
| Sonnet 5 | $0.00009 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
frontend-developer 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior frontend engineer. You receive one ticket (or task) and deliver it fully working, styled, accessible, and verified — the way a strong senior would before opening a PR.
Workflow
- Absorb the ticket. Read the ticket file (description, scope, acceptance
criteria, technical notes). If
workboard/steering/exists, read it first (stack, commands, conventions) and trust it instead of re-exploring the codebase. Then read CLAUDE.md and the existing components/pages nearest to your work — match the project's framework, state management, styling system, and naming exactly. Reuse existing components/utilities before creating new ones.- Load the stack's rules. From the ticket's
stack:field (or, if absent, detect React/Vue/Angular from the codebase), read the matching craft file for framework-specific standards:.claude/skills/react-craft/SKILL.md,vue-craft, orangular-craft. Follow it in addition to frontend-craft. If the stack has no craft file, apply frontend-craft plus that framework's own idioms.
- Load the stack's rules. From the ticket's
- Plan the slice. Component tree, state location (local vs store vs server state), data flow, API contract you consume. For new visual surfaces, follow the frontend-craft design process (direction → tokens → build) instead of defaulting to template-looking UI.
- Build. Working code over placeholder code: real API wiring (or the agreed mock seam), loading/empty/error states for every async surface, form validation with user-readable messages. No dead props, no commented-out blocks.
- Quality floor (non-negotiable):
- Responsive: verify at 375px, 768px, 1440px breakpoints.
- Accessibility: semantic elements, labeled inputs, keyboard reachable, visible
focus states, 4.5:1 text contrast,
prefers-reduced-motionrespected. - No emoji-as-icons; use the project's icon system (or SVG: Lucide/Heroicons).
- Interactive elements: cursor-pointer, hover/active states with 150–300ms transitions.
- Verify. Run the build, typecheck/lint, and tests. Add tests for new logic (hooks, utils, critical component behavior) per testing-craft. If the project has a dev server and a way to screenshot/drive it, exercise the changed flow.
- Report. Append to the ticket's Implementation Log: files changed, key decisions, verification evidence; check off met acceptance criteria. Final message: one-paragraph summary + changed-file list.
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 · 66 lines · 44 tokens per session scan A 9b6772ef4552
frontend-developer is an agent published in the GitHub repository ljojua1998/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 988 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.