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.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/instructions/aviator-coding/home-ops/agents-md)<a href="https://agentmods.dev/instructions/aviator-coding/home-ops/agents-md"><img src="https://agentmods.dev/badge/instructions/aviator-coding/home-ops/agents-md/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/instructions/aviator-coding/home-ops/agents-md"><img src="https://agentmods.dev/badge/instructions/aviator-coding/home-ops/agents-md.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 | $0.04339 | $0.04339 |
| Opus 5.5 | $0.01736 | $0.01736 |
| Sonnet 5.5 | $0.00868 | $0.00868 |
| Haiku 4.5 | $0.00434 | $0.00434 |
Grade A, and why
home-ops AGENTS.md 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 22d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Home-ops GitOps repo for a 3-node Talos Linux Kubernetes cluster managed by Flux v2. CLAUDE.md is a symlink to this file. Subsystem knowledge lives in skills (SKILL INDEX below); operator detail also in talos/AGENTS.md, bootstrap/AGENTS.md and the runbooks in skill references (SKILL INDEX below; docs/README.md lists the few that live elsewhere).
Core stack: Talos Linux + Flux v2 + Cilium (CNI, BGP LoadBalancer, kube-proxy replacement, no L2 announcements) + Rook-Ceph + External Secrets Operator/1Password + Cloudflare Tunnel + External-DNS (split: network/cloudflare-dns public, network/unifi-dns internal) + kopiur (primary backup; VolSync only on 3 carve-outs) + Gateway API (envoy-internal/envoy-external in network) + kube-prometheus-stack/Loki/Tempo/Grafana/Gatus in monitoring.
STRUCTURE
.
├── kubernetes/
│ ├── apps/base/<ns>/<app>/ # manifests (19 namespaces)
│ ├── apps/main/<ns>/ # overlay: one Flux Kustomization CR per app + kustomization.yaml
│ ├── clusters/main/ # Flux entry point: meta.yaml + apps.yaml (cluster-meta -> cluster-apps)
│ └── components/ # alerts, common, dragonfly, kopiur (+ kopiur/pvc), volsync (3 claims left)
├── talos/ # minijinja templates, rendered by `just talos`, not Flux
├── bootstrap/ # just bootstrap stages
├── .agents/skills/ # one skill per subsystem (.claude/skills is a symlink)
├── .taskfiles/ # task domains: 1password, k8s, flux, rook, network, actions-runner
├── terraform/ # OpenTofu stacks outside Flux (Authentik)
├── docs/ # tdarr harness files + pointer (docs/README.md)
└── .renovate/ # Renovate presets
WHERE TO LOOK
| Task | Location |
|---|---|
| Add app | kubernetes/apps/base/{ns}/{app}/ + overlay kubernetes/apps/main/{ns}/{app}.yaml, then - ./{app}.yaml in the overlay kustomization.yaml (skill flux-gitops) |
| Enable backups | overlay Kustomization, kopiur only; never add components/volsync to a new app (skill kopiur-backups) |
| Namespace-wide labels | kubernetes/components/common/namespace.yaml (one Namespace named not-used, renamed per overlay) |
| App secrets | {app}/app/externalsecret.yaml, ClusterSecretStore onepassword (skill secrets-1password) |
| Bootstrap secrets | bootstrap/kustomize/apps/security/, vals resolves ref+op://Home-Lab/1password/* |
| Helm/OCI repos | kubernetes/apps/base/flux-system/meta/repos/ |
| Talos config | talos/machineconfig.yaml.j2, talos/nodes/*.yaml.j2, talos/schematic.yaml.j2 (skill talos-nodes) |
| Tasks | Taskfile.yaml + .taskfiles/ (task --list-all), .justfile + */mod.just |
| CI, branch protection | .github/workflows/; ruleset on main is applied via gh api, not in Git (skill github-ci) |
| Renovate | .renovaterc.json5 + .renovate/; in-cluster CronJob is the writer (skill renovate) |
| Authentik SSO | terraform/authentik/ (skill authentik-terraform) |
| AI stack | kubernetes/apps/{main,base}/ai/ (skills ai-stack, litellm-proxy, hermes-agent, agentgateway) |
| Gatus | monitoring/gatus; endpoints come from the gatus.home-operations.com/endpoint HTTPRoute annotation (skill observability) |
| konflate | flux-system/konflate, read-only PR-review UI, internal route only; its README owns the write-back-off invariant |
| Tool versions | .mise.toml; resolve CLIs with mise which <cli> / mise exec -- <cli> |
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.
- 22d ago Changed · +29 tokens per session ee1f1ba2ac9f
- 23d ago Changed · -114 lines · -4,325 tokens per session eb73db044ef6
- 25d ago Changed · +17 lines · -23,173 tokens per session scan C → A 9f364b6151ed
- 26d ago Changed · -1,794 tokens per session b1b335b53da4
- 27d ago Changed · +1 lines · +995 tokens per session cad03575bcbd
- 28d ago Changed · +139 tokens per session 509fbeb13814
- 1mo ago Changed · +1 lines · +709 tokens per session 415d6d76441d
- 1mo ago Changed · +1 lines · +702 tokens per session 1d0f9d0ef0bb
- 1mo ago Changed · +1,514 tokens per session 40ec9c969164
- 1mo ago First seen · 254 lines · 29,543 tokens per session scan C 10d3e1f4bb5c
home-ops AGENTS.md is an instructions file published in the GitHub repository Aviator-Coding/home-ops (3 stars, last pushed today), licensed MIT. It adds 4,339 tokens to every session, about $0.0174 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).