Borrowing it
Nothing to install: this file belongs to Aviator-Coding/home-ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Aviator-Coding/home-ops/main/.agents/skills/ai-stack/SKILL.mdgit clone --depth 1 https://github.com/Aviator-Coding/home-opsWrote 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/aviator-coding/home-ops/ai-stack)<a href="https://agentmods.dev/skills/aviator-coding/home-ops/ai-stack"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/ai-stack/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.
<a href="https://agentmods.dev/skills/aviator-coding/home-ops/ai-stack"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/ai-stack.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.01261 |
| Opus 5.5 | $0.00036 | $0.00504 |
| Sonnet 5.5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
ai-stack 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 23d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI stack: inventory, ToolHive, and retirements
Namespace ai holds the agent runtime, MCP, local models, and the two
coding consumers. Routing, governance, and the B70 llama.cpp pins live in
other skills. This one owns what is deployed, how ToolHive is wired, and
what a retirement must not destroy.
Tripwires
MCPServeristoolhive.stacklok.dev/v1alpha1. Neverkagent.dev. Same kind name, different spec. kagent and kmcp were removed (PR #941, PR #942). kgateway is not deployed; non-AI ingress is Envoy Gateway innetwork.- Do not point vmcp at
ai/embedding-gpu. The optimizer re-embeds the whole catalog on every session. The GPU path was measured and rejected (batch OOM, NaN, shared card). The CPU model staysBAAI/bge-small-en-v1.5. toolhive.md talos-mcpis not live. The Talos ServiceAccount controller rejects namespaceai. Re-enable needsaiandos:readerintalos/machineconfig.yaml.j2, thenjust talos apply-nodeon all three nodes. That file is not Flux. Skilltalos-nodes.MCPServer.spec.resourceslands on the proxy Deployment, not the MCP container. A limit written there does not bound the server.- grafana-mcp's Reloader annotation sits on
spec.podTemplateSpec.metadata.annotations(secret.reloader.stakater.com/reload: toolhive-grafana). The token is injected into the MCP StatefulSet.resourceOverrides.proxyDeploymentdoes not roll that consumer. Env-injected secrets never refresh without a Reloader annotation on the workload that holds them. kubectl-mcp-readonlyhas anaggregationRule. Hand-written rules on that ClusterRole are discarded. Grants live onkubectl-mcp-readonly-base, labeled into the aggregate. The binding targets the aggregate. Core Secrets stay omitted.- Retiring an app:
grep -rn '<app>' scripts/ci/first. Several gates assertpath.is_file()on a manifest.task flux:test:allstays green either way. Never delete a kopiurSnapshotCR: its finalizer deletes the kopia snapshot. Keepai/agentmemory-ceph-20260831215039(kopiab383822fe09da5adeaf99997bc977845). retirement.md - The MCP gateway's bearer token is enforced by Envoy on the LAN route
only. vmcp has no static-token mode, so a NetworkPolicy closes the
in-cluster Service to all but envoy-internal. Consumers use
https://mcp.${SECRET_DOMAIN}/mcp. Token: 1Passwordmcp-gateway, generated and pushed bytoolhive/config. toolhive.md - opencode and repo-wiki call LiteLLM, never a provider key.
http://litellm.ai.svc.cluster.local:4000/v1via aLiteLLMVirtualKey. Skilllitellm-proxy.
What ships with it
4 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.
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.
- 23d ago Changed · +5 lines 14843c81db26
- 25d ago First seen · 80 lines · 91 tokens per session scan A 6b8b30d113c6
ai-stack is a skill published in the GitHub repository Aviator-Coding/home-ops (3 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,261 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.