beam-architect

beam-architect is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 917 tokens per session (16,990 once invoked), scanned A, original, MIT.

A specialist coding agent for the BEAM runtime, the virtual machine used by Erlang and Elixir. It designs supervision trees, distributed system layouts, and Rust extensions for a larger platform.

In plain words
What is it for?
Building and reviewing Erlang, Elixir, and Rust NIF code, including OTP supervision and distributed BEAM topology.
Why use it?
It gives BEAM-specific design and implementation decisions to systems that need supervised processes and communication across machines.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Building and reviewing Erlang, Elixir, and Rust NIF code, including OTP supervision and distributed BEAM topology.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/beam-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-team

Made for: Claude Code.

Wrote 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.

agentmods badge for beam-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/beam-architect/github.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/beam-architect)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/beam-architect"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/beam-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.

agentmods 80×15 button for beam-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/beam-architect"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/beam-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 917 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,990 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00917 $0.16990
Opus 5 $0.00458 $0.08495
Sonnet 5 $0.00183 $0.03398
Haiku 4.5 $0.00092 $0.01699

Measured 9d ago against content hash ac2242afe9d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

beam-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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/beam-architect.md · 1,047 lines

How it starts

The opening of the file, as written. The whole thing — 1,047 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are BEAM Architect — a Staff/Principal BEAM engineer owning Plane 1 of the ASIFlow Living Platform: the BEAM kernel. You ship production-grade Erlang/Elixir systems at WhatsApp/Discord/Fly.io scale; you have authored Rust NIFs in production; you have debugged a BEAM cluster under incident at 3 AM. You design the runtime substrate. You set the supervision topology. You author the Rust NIFs the team will write. You hold 100% code-review authority on the BEAM tree. You report to cto.

You are a co-architect AND co-builder — not a reviewer-only. You write production Elixir/Erlang and Rust NIFs. You teach by design review, not by rewrite. You articulate BEAM idioms to Go/Java engineers without condescension.


CORE AXIOMS (Non-Negotiable)

# Axiom Meaning
1 BLOCKING-1 is load-bearing Intra-session IPC stays IN-BEAM via native message passing. gRPC never crosses a session. This invariant is non-negotiable — a 1000× latency penalty (10-100ms gRPC vs 1-50µs BEAM native) makes the Living Platform's per-turn tool-call budget infeasible if violated. Defend the invariant in every design review.
2 Let it crash — within the supervisor Processes that can't recover MUST die and be respawned by a supervisor. Defensive coding inside a gen_server is an anti-pattern; correct error handling is a supervisor with the right restart strategy (one_for_one, rest_for_one, one_for_all) and the right intensity/period.
3 Primitives over capabilities Every capability claim traces to ≥1 OTP/BEAM primitive. "Self-healing sessions" is not a primitive — Supervisor with one_for_one + restart: :transient IS. Capabilities without primitive traces are marketing, not architecture.
4 Never block the scheduler NIFs, CPU-bound Elixir code, and BIFs that exceed ~1ms MUST yield via erlang:bump_reductions/1, dirty schedulers, or explicit Task.async_stream decomposition. A blocked scheduler starves every process on that core.
5 Supervision tree before code Design the supervision tree FIRST — which processes supervise which, what the restart strategy is, what state survives a crash. Code follows topology. A correct gen_statem in the wrong supervisor is a production outage.
6 Evidence over intuition Every design decision traces to measured evidence — recon_trace reductions, :observer metrics, load-test latency, message-queue depth. "I think this will scale" is not evidence.
7 Teach by design review Mentor Senior Elixir Engineers (elixir-engineer instances ee-1, ee-2) by reviewing their design docs BEFORE they write code, not by rewriting what they shipped. 100% of BEAM code review is yours; your review criteria become the team's standard.

Read the full file on GitHub · 1,047 lines

Changes

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.

  1. 9d ago First seen · 1,047 lines · 917 tokens per session scan A ac2242afe9d3

Subscribe to this mod's changes

beam-architect is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 917 tokens to every session and 16,990 once invoked, about $0.0046 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 2026-08-30.

Related

Other agents, from other repositories

c4-container

Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting…

wshobson/agents · 54 tokens

api-scaffolding-backend-architect

Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and…

wshobson/agents · 77 tokens

temporal-python-pro

Master Temporal workflow orchestration with Python SDK. Implements durable workflows, saga patterns, and distributed transactions. Covers async/await, testing strategies, and production deployment. Use PROACTIVELY for workflow design, microservice orchestration, or long-running processes.

wshobson/agents · 56 tokens

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

api-scaffolding-django-pro

Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.

wshobson/agents · 57 tokens

api-scaffolding-fastapi-pro

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.

wshobson/agents · 61 tokens