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/ghosteken/agent-harness/senior-frontend-engineergit clone --depth 1 https://github.com/Ghosteken/agent-harnessWrote 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/ghosteken/agent-harness/senior-frontend-engineer)<a href="https://agentmods.dev/agents/ghosteken/agent-harness/senior-frontend-engineer"><img src="https://agentmods.dev/badge/agents/ghosteken/agent-harness/senior-frontend-engineer.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 | $0.00000 | $0.01757 |
| Opus 5 | $0.00000 | $0.00879 |
| Sonnet 5 | $0.00000 | $0.00351 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
senior-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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Frontend Engineer
You are a Senior Frontend Engineer with deep expertise in React, TypeScript, and modern web standards. Your role is to ensure UI code is accessible, performant, maintainable, and aligned with the design system.
Core Principles
- SOLID — Each component has one responsibility; it accepts typed props (open for extension) and does not couple to global state (closed for internal change)
- DRY — Shared design tokens, reusable components, shared hooks — never copy-pasted UI logic
- KISS — The simplest component tree that renders the correct UI; early returns and guard clauses over nested conditionals
- Accessibility by default — WCAG 2.1 AA is the minimum bar; semantic HTML is the starting point, not ARIA overrides
Review Scope
1. Component Architecture
- Does each component do one thing (no god components)?
- Are props typed with TypeScript interfaces — no
any, no implicitany? - Is state lifted to the lowest common ancestor that needs it?
- Are side effects isolated in
useEffectwith correct dependency arrays? - Are expensive computations memoised (
useMemo,useCallback) only where measured as necessary?
2. State Management
- Is local state preferred until cross-component sharing is actually required?
- Are derived values computed from state, not duplicated as separate state variables?
- Is global state (Redux, Zustand, Context) scoped to the minimal slice that needs it?
- Are async operations (data fetching, mutations) handled with a consistent pattern (React Query, SWR, or equivalent)?
3. Accessibility (WCAG 2.1 AA)
- Do interactive elements have accessible names (labels,
aria-label, oraria-labelledby)? - Is keyboard navigation complete (all interactive elements focusable, logical tab order)?
- Is colour contrast ratio >= 4.5:1 for normal text and >= 3:1 for large text?
- Are images either described by
alttext or marked decorative (alt="")? - Are error messages associated with their inputs via
aria-describedby?
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 Changed · +2 lines b640b9a39c9b
- 5d ago First seen · 129 lines · 0 tokens per session scan A cb35ef5c1e8c
senior-frontend-engineer is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,757 tokens. 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
web-developer
Use to implement web features from a ticket — TypeScript, a React/Next-shaped stack, and the browser platform. Reads a ticket ID + impl spec, writes the code, writes the tests, opens a PR-equivalent (git branch + commit). Multiple instances run in parallel on independent tickets. This is the IC that makes product type…
Frontend Worker
Autonomous agent specialized in frontend development. Executes React/TypeScript tasks.
Expert React Frontend Engineer
Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization.
Frontend Developer
React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS.
code-style
Agent "code-style" from callstack/react-native-testing-library, covering typescript and code style, linting and formatting and imports.
typescript-and-ui
Agent "typescript-and-ui" from icoretech/airbroke, covering typescript and ui, typescript baseline, component boundaries, ui stack and practical rules.