domain-docs

domain-docs is a skill for Claude Code, Codex from gavinmcfall/home-ops. It costs 58 tokens per session (1,917 once invoked), scanned A, original, MIT.

Generate, update, and audit per-domain docs (docs/domains/) from kubernetes manifests. Use when creating a domain doc set, refreshing docs after cluster changes, or checking for doc drift. Modes: create , update , audit.

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/gavinmcfall/home-ops/domain-docs
Any agent
npx skills add gavinmcfall/home-ops --skill domain-docs
Clone the repo
git clone --depth 1 https://github.com/gavinmcfall/home-ops

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for domain-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/gavinmcfall/home-ops/domain-docs.svg)](https://agentmods.dev/skills/gavinmcfall/home-ops/domain-docs)
Your own site
<a href="https://agentmods.dev/skills/gavinmcfall/home-ops/domain-docs"><img src="https://agentmods.dev/badge/skills/gavinmcfall/home-ops/domain-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,917 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 $0.00058 $0.01917
Opus 5 $0.00029 $0.00958
Sonnet 5 $0.00012 $0.00383
Haiku 4.5 $0.00006 $0.00192

Measured 2d ago against content hash c58d6c87997e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-docs 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 2d 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.

.claude/skills/domain-docs/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Docs

Produce structurally identical, manifest-accurate domain documentation. Spec: docs/superpowers/specs/2026-08-15-domain-docs-skill-design.md.

Inputs

  • domains.yaml (this directory) — the ONLY source of domain membership.
  • kubernetes/apps/<ns>/<app>/ (+ flux/ if needed) — the ONLY source of generated facts. Read per app: ks.yaml (Flux Kustomization: dependsOn, components), app/helmrelease.yaml (chart, image, env, route, persistence), app/*.yaml (externalsecret, pvc, httproute if split out).
  • templates/ (this directory) — structure of every output file.

Membership resolution

namespaces minus exclude plus include (entries are <ns>/<app> paths). An app may appear in multiple domains; each mention links to the owning domain's context.md for depth. Any app under a registry-claimed namespace that resolves to no domain → drift report. Never guess membership.

Membership is one member per leaf directory that contains its own ks.yaml under a claimed namespace path — a grouping directory (e.g. exporters/) is not itself a member, it enumerates its leaf children. include/exclude entries are taken literally as written and may carry intermediate path segments (e.g. observability/exporters/blackbox-exporter). The Apps table's Namespace column reports the leaf's ks.yaml spec.targetNamespace (where its resources actually land), which can differ from the claimed namespace the directory lives under — membership still follows the owning directory, not targetNamespace. The Apps table's DependsOn column is sourced from ks.yaml spec.dependsOn only (Kustomization-level, Flux ordering); a HelmRelease's own spec.dependsOn is a different, unrelated field and is never surfaced in that column.

One-liner descriptions

The overview.md Components "What it does" column must be deterministic — resolve each app's one-liner via this precedence, stopping at the first hit:

  1. domains.yaml<domain>.descriptions.<app>, if the registry entry has a descriptions: map with this app as a key. Registry-authored text always wins.
  2. The app's gethomepage.dev/description route annotation, used verbatim — no editorial extensions, no appended clauses. A commented-out annotation is not a source and does not count.
  3. Fixed fallback string: No description — add one to domains.yaml or a gethomepage annotation.

Read the full file on GitHub · 161 lines

Files

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.

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. 2d ago First seen · 161 lines · 58 tokens per session scan A c58d6c87997e

Subscribe to this mod's changes

domain-docs is a skill published in the GitHub repository gavinmcfall/home-ops (37 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,917 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 2026-09-01.

Related

Other skills, from other repositories