devops

An operations guide for diagnosing running Ergo Framework clusters, which are groups of connected Go processes that communicate through actors and messages.

In plain words
What is it for?
Use it to inspect processes, mailboxes, memory, networks, event fanout, restart loops, and stuck actors through the Ergo MCP connection.
Why use it?
It gives structured investigations for production problems instead of treating every symptom as a generic checklist, including liveness and active or passive sampling.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ergo-services/claude/devops
Any agent
npx skills add ergo-services/claude --skill devops
Clone the repo
git clone --depth 1 https://github.com/ergo-services/claude

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.01045
Opus 5 $0.00036 $0.00522
Sonnet 5 $0.00014 $0.00209
Haiku 4.5 $0.00007 $0.00104

Measured yesterday against content hash c1a41b0e9ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops 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 yesterday.

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.

skills/devops/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ergo DevOps

Diagnose production issues in running Ergo Framework distributed systems via the MCP application (ergo.services/application/mcp). This skill is the operational counterpart to the framework skill - it assumes the system is running and something is suspect.

MCP Connection

Add the MCP endpoint to Claude Code:

claude mcp add --transport http ergo http://localhost:9922/mcp

Or with authentication:

claude mcp add --transport http ergo http://localhost:9922/mcp --header "Authorization: Bearer ${MCP_TOKEN}"

Network Transparency

Every tool accepts a node parameter. When you pass node=X, the MCP entry-point forwards the request to node X via native Ergo inter-node protocol. The framework establishes the connection automatically — never call network_connect just to query.

The MCP entry-point node is not privileged. Always pass node explicitly even for it.

Reference Files

Topic File When to read
Full tool catalog: 48 MCP tools across 11 categories with parameters, defaults, output shape references/tools.md Any investigation
Process model: states, mailbox queues, metrics (RunningTime, Drain, MailboxLatency), liveness formula references/process-model.md Interpreting process_list / process_info / process_inspect
Counters: node_info, network_info, process_info, event_info with per-field meaning and diagnostic use references/counters.md Reading any *_info output
10 diagnostic playbooks (cluster health, bottleneck, CPU, memory, leak, restart loop, zombies, network, events, goroutines) references/playbooks.md Any symptom matching a playbook
Framework internals: Important-delivery errors, restart intensity sliding window, pool backpressure, connection pool, event fanout, shutdown signals references/framework-internals.md Explaining counter behavior or error semantics
Samplers: active (periodic tool), passive (log/event listen), proxy samplers, typed-message injection references/samplers.md Trend analysis, reproducing transient issues
Build tags: pprof, latency, verbose, norecover, typestats; what each enables and what breaks without them references/build-tags.md Interpreting missing metrics or goroutine data

Read the full file on GitHub · 61 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 61 lines · 71 tokens per session scan A c1a41b0e9ad0

Subscribe to this mod's changes

devops is a skill published in the GitHub repository ergo-services/claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,045 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens