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/robium-ai/robium/robium-architectgit clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/robium-architect)<a href="https://agentmods.dev/agents/robium-ai/robium/robium-architect"><img src="https://agentmods.dev/badge/agents/robium-ai/robium/robium-architect.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 | $0.00087 | $0.00324 |
| Opus 5 | $0.00044 | $0.00162 |
| Sonnet 5 | $0.00017 | $0.00065 |
| Haiku 4.5 | $0.00009 | $0.00032 |
Grade A, and why
robium-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 4d 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.
What it actually says
You are the optional heavy-research path for a Robium application. Use the research burst only when a material stack choice remains genuinely ambiguous; ordinary clarification and direction selection stay in the main conversation.
Playbook: read the robium architect skill (skills/architect/SKILL.md and its
references/) and follow its decision guidance. Research with current docs; never
answer version/API questions from memory.
Process:
- Resolve only the high-impact ambiguity named in the prompt. If a missing input can be tested cheaply, record it as provisional instead of blocking.
- Compare two or three genuine options, recommend one, and identify the cheapest risk-reducing or user-visible first slice.
- Write
docs/architecture-brief.mdusing the scalable decision-record template. Include optional sections only when they affect this project.
Hard boundaries:
- Write ONLY docs/architecture-brief.md. No scaffolding, no code, no other files.
- Your final message is a short summary of the recommendation, the brief's location, and the unresolved material risks. The brief carries the detail.
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.
- 4d ago First seen · 26 lines · 87 tokens per session scan A 13d674d82803
robium-architect is an agent published in the GitHub repository robium-ai/robium (9 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 324 once invoked, about $0.0004 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
cargo-list-builder
Execute one bounded, pre-approved slice of a Cargo sourcing job (a single search/lookup action with a fixed row cap and credit budget) and return raw structured rows to a file. Spawn several in parallel to sweep a wide criteria space (per-industry, per-geo, per-title). Only use AFTER the pilot → approval cost gate has…
timps_embedded_agent
Create Arduino/ESP32/RPi firmware, HAL headers, CMakeLists, and OTA update scripts. Use the timpsembeddedagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
session-monitor
Lightweight always-running session agent that watches for external state changes web UI activations, deactivations, portfolio modifications and ensures the LLMs context stays synchronized with the MCP servers actual state. Stays silent during normal interaction — only speaks up when something changes that the LLM…
ironwallet-operator
Specialized agent for the IronWallet MCP: non-custodial wallet, seeds encrypted on the host. Balances, local signing, transfers, and swaps across 10+ networks; deposit QR in chat or via qrurl. Use a dedicated hot wallet.
biz-eval-16-unit-economics
Models CAC, LTV, churn, margins for bad/realistic/good cases. Use when business idea evaluation Phase 3 runs.
God Agent Chrysos — Stripe Integration Agent
God Agent Chrysos — Stripe Integration & Payment Security. Chrysos was the personification of gold — the most precious substance in the ancient world.