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 skills/alobarquest/infraops-mcp-server/skillnpx skills add AlobarQuest/infraops-mcp-server --skill skillgit clone --depth 1 https://github.com/AlobarQuest/infraops-mcp-serverWrote 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/skills/alobarquest/infraops-mcp-server/skill)<a href="https://agentmods.dev/skills/alobarquest/infraops-mcp-server/skill"><img src="https://agentmods.dev/badge/skills/alobarquest/infraops-mcp-server/skill.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 5.1 | $0.00162 | $0.00812 |
| Opus 5 | $0.00081 | $0.00406 |
| Sonnet 5 | $0.00032 | $0.00162 |
| Haiku 4.5 | $0.00016 | $0.00081 |
Grade A, and why
infraops-escalation 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 5d 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.
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.
Escalate to the InfraOps provider agent
The infraops MCP exposes ~195 infrastructure tools. When you need something it
doesn't expose — no tool for an operation, a tool missing a parameter, an
unsupported provider endpoint — you don't have to give up or hand it to Devon.
You can escalate to the infraops provider agent: a gated agent running inside
~/Projects/infraops-mcp-server that can reason about the server and add or
extend a tool to close the gap.
This is an escalation lane, not basic usage. If the MCP already has a tool for what you need, just call it.
When to escalate
- The capability you need has no infraops tool at all.
- An existing tool is close but missing a parameter / option you need.
- A provider endpoint isn't covered and adding it is in scope for infraops.
When NOT to escalate
- Routine work an existing tool covers → just call the tool.
- The fix is an infrastructure mutation (deploy, restart, destructive op) → that's Devon's call; the provider agent will refuse it and emit it as a PROPOSAL anyway.
How to escalate
~/Projects/infraops-mcp-server/bin/provider-agent --session <short-issue-name> \
"Doing <infra task> for <app>. I need <capability> but the infraops MCP has no
tool for it / tool <name> lacks <param>. Here's what I tried and the exact error: …"
Give it full context: the operation you need, the closest existing tool (if any),
what you tried, and exact errors. Reuse one --session name per issue so the
thread keeps context across turns.
Read the STATUS: block in the reply
resolved— the provider agent added/extended the tool. Its edits are on aprovider-agent/<session>review branch in~/Projects/infraops-mcp-server(the reply's[provider-agent] … committed to <branch> @ <sha>line names it). The new tool is not live yet: Devon reviews/merges the branch, then the MCP is rebuilt (npm run build) and reloaded before the tool can be called. Surface this to Devon; don't assume the tool is immediately callable.needs-info— it needs more from you. Answer precisely and call again with the same--sessionname.needs-devon— closing the gap needs an infra mutation or a build/publish only Devon should authorize. Stop and surface thePROPOSALSblock to Devon.
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.
- 5d ago First seen · 61 lines · 162 tokens per session scan A 6137178d287f
infraops-escalation is a skill published in the GitHub repository AlobarQuest/infraops-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 812 once invoked, about $0.0008 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…