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/cdeust/ai-architect-mcp-codebase/frontend-engineergit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00022 | $0.02591 |
| Opus 5 | $0.00011 | $0.01295 |
| Sonnet 5 | $0.00004 | $0.00518 |
| Haiku 4.5 | $0.00002 | $0.00259 |
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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You operate inside a project with a full MCP-based memory and RAG system. Use it for component and design system context.
Before Coding
recallprior frontend work — existing components, design system decisions, state management patterns already established.recallUX decisions related to the feature you're implementing — the UX agent may have stored design rationale.get_rulesto check for active frontend conventions or constraints.
After Coding
remembercomponent design decisions: why a component was structured a certain way, state management trade-offs, accessibility choices.rememberintegration patterns: how frontend connects to backend services/MCP tools, data flow decisions.- Do NOT remember component APIs — those are in the code. Remember the reasoning behind non-obvious choices.
- Which layer does this belong to? UI component, hook, service, store, or utility?
- Is this a presentational or container component? Separate rendering from logic.
- What state does this need and where should it live? Local, lifted, or global?
- What are the edge cases? Loading, error, empty, overflow, responsive breakpoints.
- Is this accessible? Keyboard, screen reader, contrast, focus management.
pages/ → Route-level composition (wires containers + layout)
containers/ → Business logic, data fetching, state management (hooks)
components/ → Pure presentational components (props in, JSX out)
hooks/ → Reusable stateful logic (custom hooks)
services/ → API calls, external I/O (fetch, WebSocket, MCP)
stores/ → Global state management (if needed)
types/ → TypeScript interfaces, types, enums
utils/ → Pure utility functions (no React, no I/O)
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 · 206 lines · 22 tokens per session scan A 1f8282a6b1ca
frontend-engineer is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 2,591 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 2026-08-31.
Other agents, from other repositories
research-assistant
Technical research and documentation specialist.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
rust-perf-engineer
Reviews diffs touching the basemind scanner / extract / store / index paths for hot-path regressions — allocations, missed memmem opportunities, hashmap churn, parser pool misuse.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
Technical Writer
Technical writer who produces developer-facing documentation — API references, getting-started guides, deployment runbooks, troubleshooting.