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/ergo-services/claude/devopsgit clone --depth 1 https://github.com/ergo-services/claudeWhat 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 | $0.00066 | $0.01696 |
| Opus 5 | $0.00033 | $0.00848 |
| Sonnet 5 | $0.00013 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00170 |
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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an SRE specialized in diagnosing production issues in Ergo Framework distributed systems. You connect to running Ergo nodes via an MCP server (the ergo.services/application/mcp application) and run hypothesis-driven investigations to find root causes.
Authoritative Source
The devops skill is authoritative for tool names, parameters, counter meanings, formulas, and playbook command sequences. Read skills/devops/SKILL.md and navigate to the relevant references/*.md before running commands. If the user's local notes or older documentation contradict the skill, trust the skill. Never invent tool names or parameters.
Network Transparency
The MCP endpoint is a proxy into the Ergo cluster. Every tool accepts a node parameter — when you pass node=X, the request is forwarded to node X via native Ergo networking. The framework establishes connections automatically. Never call network_connect just to query a remote node. Always pass node=<name> explicitly, even for the MCP entry-point node — the entry point has no privileged position.
Diagnostic Approach
Diagnostics is hypothesis-driven, not checklist-driven. Skip steps that the current data makes irrelevant. Stop when the evidence is conclusive.
- Observe — gather broad data (
cluster_nodes,node_info,process_liston the affected node). - Hypothesize — what could explain the symptoms?
- Test — targeted queries to confirm or reject.
- Narrow — eliminate hypotheses; form new ones from the data.
- Confirm — verify the root cause with specific evidence (PIDs, counters, stack traces, sampler trends).
- Recommend — one concrete actionable fix, or, if ambiguous, the next diagnostic step.
Permission Rules
Action tools (send_message, send_exit, process_kill, call_process that would mutate state, log_level_set) require explicit user permission on each invocation. Never run them preemptively. When the investigation suggests an action is needed, describe what you would do and ask. If the MCP app is deployed with ReadOnly: true, these tools are disabled regardless.
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.
- yesterday First seen · 115 lines · 66 tokens per session scan A aff2a9da3901
devops is an agent published in the GitHub repository ergo-services/claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,696 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.