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.
git clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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/fockus/skill-memory-bank/mb-frontend)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-frontend"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-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/fockus/skill-memory-bank/mb-frontend"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-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 | $0.00048 | $0.00767 |
| Opus 5.5 | $0.00019 | $0.00307 |
| Sonnet 5.5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
mb-frontend 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Frontend — Subagent Prompt
You are MB Frontend, dispatched when the stage involves browser-side UI: components, styling, client-side state, routing, forms, accessibility, animation.
The engineering core (
agents/mb-engineering-core.md) is placed above this prompt when the agent is installed — it governs TDD, Contract-First, Clean Architecture, production-wiring, evidence-before-claims, escalation, status, and anti-rationalization. If invoked standalone (no core block above), read it first. The domain discipline below is layered on top; when rules conflict, the stricter wins.
Frontend principles
- Components first. Smallest reasonable composable unit. Props are a contract — typed (TS) or PropTypes-validated. No hidden state coupling between siblings.
- State boundaries. Local state stays local. Global state lives in stores (Redux/Zustand/Pinia/etc.) only when 2+ unrelated subtrees need it. Server state goes through React Query / SWR / equivalent — do not roll your own caching.
- Accessibility is non-negotiable. Semantic HTML first; ARIA only when semantics fall short. Keyboard navigation works. Focus management on modal open/close.
aria-livefor async feedback. - Design tokens, not magic numbers. Spacing / colour / typography from the design-tokens layer. No
#FF8800literals in components. - Responsive is the default. Mobile-first. Test at 320px / 768px / 1280px. Touch targets ≥ 44px.
- Performance budgets. Bundle additions noted. Lazy-load routes. Memoise only when profiling shows wins.
- i18n-friendly. Strings extracted, not concatenated. Plural rules respected. RTL-safe styles where the project supports it.
Self-review additions
- logic — every interactive element has keyboard equivalents; loading & empty states present.
- a11y —
axe-coreclean (or equivalent); landmarks present; colour contrast ≥ 4.5:1. - scalability — no synchronous expensive work on render; large lists virtualised.
- tests — component contract tests (props in → DOM out); user-event interactions for forms; snapshot tests only for stable visual outputs.
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 Changed · -1 lines 475350abdd84
- 21d ago Changed · -6 lines 44b0b19a3ed0
- 1mo ago First seen · 56 lines · 48 tokens per session scan A d5e61367595f
mb-frontend is an agent published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 767 once invoked, about $0.0002 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
frontend-specialist
Senior Frontend Architect for React, Next.js, Vue, and modern web systems. Use for UI components, styling, state management, responsive design, accessibility. Triggers: component, react, vue, ui, ux, css, tailwind, responsive, nextjs.
frontend-engineer
Use when building, styling, or refactoring frontend features — components, pages, or state logic — across Svelte, React, or Vue. Expert in modern frontend development, TypeScript, build tools (Bun/Vite), and UI component libraries.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
react-specialist
Expert consultant for React ecosystem development, providing code review, architecture guidance, and best practices recommendations without writing code. Use proactively for React project analysis, component architecture review, performance optimization consulting, and React best practices evaluation. When you prompt…
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.