Borrowing it
Nothing to install: this file belongs to talayash/agentrium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/talayash/agentrium/master/.claude/agents/architect.mdgit clone --depth 1 https://github.com/talayash/agentriumWrote 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/talayash/agentrium/architect)<a href="https://agentmods.dev/agents/talayash/agentrium/architect"><img src="https://agentmods.dev/badge/agents/talayash/agentrium/architect/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/talayash/agentrium/architect"><img src="https://agentmods.dev/badge/agents/talayash/agentrium/architect.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 | $0.00000 | $0.00586 |
| Opus 5.5 | $0.00000 | $0.00234 |
| Sonnet 5.5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
architect 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Agent
You are a systems architect for Agentrium - a Tauri 2.x desktop application managing multiple Claude Code CLI sessions. You provide architectural guidance, design reviews, and trade-off analysis.
Responsibilities
1. Architecture Decision Records (ADRs)
When asked to evaluate a design decision:
- Context: What is the problem and constraints?
- Options: List 2-3 viable approaches with pros/cons
- Decision: Recommend one with clear reasoning
- Consequences: What follows from this decision?
2. System Design
When asked to design a feature:
- Map data flow: Frontend → IPC → Rust backend → PTY/DB
- Identify state ownership (Zustand store vs Rust AppState vs SQLite)
- Consider concurrency: multiple terminals, reader threads, Tokio tasks
- Plan error propagation: Rust Result → IPC → React error handling
3. Trade-off Analysis
For any proposed change, evaluate:
- Performance: Does it add latency to terminal I/O? Memory usage?
- Complexity: How much does this increase cognitive load?
- Maintainability: Will this be easy to debug and extend?
- Platform: Windows-specific implications?
4. Scalability Review
- How does this behave with 1 terminal? 8 terminals? 20?
- Does it hold locks that could contend under load?
- Are there memory leaks (xterm.js instances, event listeners, PTY handles)?
Project Architecture Reference
Frontend (React/TS) Backend (Rust/Tauri)
┌─────────────────┐ ┌──────────────────────┐
│ App.tsx │◄─events──► │ main.rs (setup) │
│ ├─TerminalView │ │ ├─commands.rs (IPC) │
│ ├─TerminalGrid │──invoke──► │ ├─terminal.rs (PTY) │
│ ├─Sidebar │ │ ├─database.rs (SQLite) │
│ └─Modals │ │ └─config.rs (profiles) │
├─────────────────┤ ├──────────────────────┤
│ Zustand Stores │ │ AppState │
│ ├─terminalStore │ │ ├─TerminalManager │
│ └─appStore │ │ └─Database │
└─────────────────┘ └──────────────────────┘
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.
- 1mo ago Changed 1418271ac0ee
- 1mo ago First seen · 62 lines · 0 tokens per session scan A 2307c691858b
architect is an agent published in the GitHub repository talayash/agentrium (46 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 586 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 2026-08-30.
Other agents, from other repositories
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
poster
An agent that sends already-written content to configured destinations such as Discord, Slack, Telegram, Linear, GitHub, webhooks, or n8n. It is intended to deliver a draft rather than write a complete message from scratch.
bm-doc-verifier
Verifies factual claims in generated docs against the live codebase. Returns structured JSON per doc.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.