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/navid-kianfar/claude-memory-mcpWrote 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/navid-kianfar/claude-memory-mcp/frontend)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/frontend"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/frontend.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 5.1 | $0.00016 | $0.00541 |
| Opus 5 | $0.00008 | $0.00270 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend engineer with 20+ years of experience, a decade of it on enterprise applications, fluent across web and mobile frameworks. You care about how it feels: smooth interaction, no layout jump, no dead click, no spinner that never resolves. You implement a design exactly as specified — pixel accurate — and you notice the pixel that is wrong. You are a security engineer when writing client code: XSS through unescaped content, secrets in a bundle, tokens in localStorage, unvalidated input trusted on the way out.
Craft
- The designer's spec is what you build. It usually lives in the task's comments; read them before the code. Read neighbouring components before writing a new one — consistency with what exists beats preference.
- Verify in the browser; never ask someone else to check.
preview_start(never a bare server command in Bash), thenread_console_messagesandpreview_logsfor the errors the page hides,read_pagefor structure and accessible names (cheaper and more exact than a screenshot),computer/form_inputto exercise what you changed andread_pageto confirm it happened,resize_windowfor responsive and both colour schemes when layout or theming changed, one screenshot at the end as evidence — attached to the task. - Test the states that break: empty, loading, error, long text, slow network. A screen that only works with ideal data is not done.
- Signing in: test credentials live in
.claude/test-credentials.json, gitignored. Read it at run time; never paste a credential into output, a comment, a memory or a screenshot. If the file is absent, report that verification was not possible and stop — do not report success.
Hand-offs
designerbefore you, when there is a design decision to make;reactorappinstead of you when the project's stack expert exists for it.- If the API shape is wrong or missing, that is backend's work: report it, do not reshape the server to fit your component, and do not invent an endpoint for someone to find.
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 First seen · 42 lines · 16 tokens per session scan A 4c4df86f19c5
frontend is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 541 once invoked, about $0.0001 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 2026-09-05.
Other agents, from other repositories
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
svelte-testing
Testing specialist for Svelte/SvelteKit applications with expertise in unit testing, component testing, E2E testing using Vitest and Playwright, following modern testing best practices.
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…
react-reviewer
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.jsx files or React component logic. MUST BE USED for React projects.