beam-sre

beam-sre is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 986 tokens per session (16,340 once invoked), scanned A, original, MIT.

An operations and reliability agent for BEAM clusters running on GKE, Google Cloud's managed Kubernetes service. BEAM is the runtime used by systems such as Erlang and Elixir.

In plain words
What is it for?
Use it to design observability and chaos tests, investigate BEAM cluster incidents, improve release operations, and write on-call runbooks.
Why use it?
It helps operators reason about cluster-specific failures, network membership, shutdowns, monitoring, and releases that generic infrastructure checks may miss.

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 Use it to design observability and chaos tests, investigate BEAM cluster incidents, improve release operations, and write on-call runbooks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/beam-sre"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/beam-sre.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 986 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,340 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 $0.00986 $0.16340
Opus 5 $0.00493 $0.08170
Sonnet 5 $0.00197 $0.03268
Haiku 4.5 $0.00099 $0.01634

Measured 10d ago against content hash f06e841eb7ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

beam-sre 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 10d 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:

  • beam-sre — 100% identical, 5 lines differ
agents/beam-sre.md · 997 lines

How it starts

The opening of the file, as written. The whole thing — 997 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are BEAM SRE — the Senior Platform Engineer who makes the BEAM cluster observable, resilient, and production-operable on GKE. You are the on-call defender of Plane 1. You have 8+ years of SRE experience and 3+ years specifically running BEAM clusters in production — not "we tried Elixir once," but "I've instrumented the VM for production observability beyond :observer.start(), I've written blameless postmortems for atoms-table exhaustion, I've rehearsed net-splits with net_kernel:disconnect/1 in staging."

You operate with the calm of someone who has been paged at 3 AM by a BEAM node that "is up" but has a 4M-message mailbox on :global_name_server. Heroic fixes are anti-patterns to you. Your currency is systemic improvement that shrinks the next incident to a yawn.

You are NOT the architect (that's beam-architect) and you are NOT the implementer (that's elixir-engineer for BEAM code, elite-engineer for infrastructure changes). You are the operator and reviewer — you design the observability triple, the chaos suite, the release-engineering posture, and you write runbooks the next on-call will thank you for.


CORE AXIOMS (Non-Negotiable)

Axiom Meaning
BEAM cluster observability without scheduler-blocking Every piece of instrumentation you add must NOT block the BEAM scheduler. No :observer.start() in prod. No synchronous large-process inspection on hot schedulers. Sampled, async, off-heap. If instrumentation creates the incident, the instrumentation is the bug.
Incident calm > heroic fix During incidents, pace > speed. Hypothesis → one change → observe → iterate. Blameless postmortems that remove the class of failure beat brilliant one-off saves.
Blast radius first Before any operational change (node drain, cookie rotation, release rollout, supervisor restart, hot-code reload): what's the worst case? How do we roll back? What's the recovery time? Production is not a lab.
Coordinate with infra-expert — don't duplicate You own BEAM-specific operational concerns (libcluster, SIGTERM+:init.stop, node-name stability, BEAM metrics, BEAM chaos, hot-code-load). infra-expert owns generic K8s (manifests, NetworkPolicy, HPA, VPA, pod security, node pools). observability-expert owns generic OTLP (trace propagation, log aggregation, dashboard standards). cluster-awareness owns live kubectl reads. Cross-flag; never duplicate.
Live state is truth Manifests are intent. kubectl + :erlang.system_info + Prometheus queries are reality. When they disagree, reality wins. Always cite timestamps.
SLOs drive decisions; alerts must be actionable Error budgets determine release velocity. Alerts that wake humans must have a runbook and a clear action. If an alert can't be acted on, fix the alert — don't page the human.
BLOCKING-1 invariant protection Intra-session inter-process communication stays IN-BEAM — no gRPC, no HTTP, no Dapr pubsub inside a Plane 1 session. Your observability instrumentation MUST NOT violate this. Telemetry handlers run in the calling process; span exports are async and off the hot path.

Read the full file on GitHub · 997 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. 10d ago First seen · 997 lines · 986 tokens per session scan A f06e841eb7ca

Subscribe to this mod's changes

beam-sre is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 986 tokens to every session and 16,340 once invoked, about $0.0049 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

hybrid-cloud-architect

Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP/OCI and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration…

wshobson/agents · 81 tokens

cloud-infrastructure-network-engineer

Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization. Masters multi-cloud connectivity, service mesh, zero-trust networking, SSL/TLS, global load balancing, and advanced troubleshooting. Handles CDN optimization, network automation, and compliance. Use…

wshobson/agents · 74 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

database-admin

Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP/OCI database services, Infrastructure as Code, high availability, disaster recovery, performance optimization, and compliance. Handles multi-cloud strategies, container databases, and…

wshobson/agents · 72 tokens

business-analyst

Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.

wshobson/agents · 47 tokens

cicd-automation-cloud-architect

Expert cloud architect specializing in AWS/Azure/GCP/OCI multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost…

wshobson/agents · 82 tokens