bex: Skill for Claude Code

.claude/skills/deploy-app-from-local/SKILL.md

deploy-app-from-local is a skill for Claude Code, Codex from bex-co/bex. It costs 58 tokens per session (1,557 once invoked), scanned A, original, Apache-2.0.

A runbook for deploying code from a local checkout to a live application on Hetzner, a cloud hosting provider.

In plain words
What is it for?
Building the current local code into a container image, importing it manually, and updating the specified production application after confirming the scope.
Why use it?
The production setup cannot build the application from Git inside the cluster, and restarting only reuses the existing image instead of deploying new code.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present.

This is bex-co/bex's own configuration. It tells Claude Code and Codex how to work on bex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bex configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is BEX_SSH_KEY_PATH=~/.ssh/id_bex bash scripts/fetch-app-kubeconfig.sh /tmp/bex-app.kubeconfig.

Reuse

Borrowing it

Nothing to install: this file belongs to bex-co/bex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bex-co/bex/main/.claude/skills/deploy-app-from-local/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bex-co/bex

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 deploy-app-from-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/bex-co/bex/deploy-app-from-local.svg)](https://agentmods.dev/skills/bex-co/bex/deploy-app-from-local)
Your own site
<a href="https://agentmods.dev/skills/bex-co/bex/deploy-app-from-local"><img src="https://agentmods.dev/badge/skills/bex-co/bex/deploy-app-from-local.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 1,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00058 $0.01557
Opus 5 $0.00029 $0.00779
Sonnet 5 $0.00012 $0.00311
Haiku 4.5 $0.00006 $0.00156

Measured 6d ago against content hash b416593e60eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deploy-app-from-local scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(git:*), Bash(docker:*), Bash(ssh:*), Bash(scp:*), Bash(curl:*), Bash(kubectl:*), Bash(python3:*)
.claude/skills/deploy-app-from-local/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: deploy a local checkout to prod Hetzner (manual image-import runbook)

There is no build-from-git-in-cluster shortcut. App.spec.repo + the operator's build.Build() (lego/operator/internal/build/build.go) is unimplemented in prod: the deployed operator image is distroless/static:nonroot (lego/Dockerfile) with no git/docker/pack binaries and no volumes (lego/operator/config/manager/manager.yaml). The original demo built locally and ctr-imported by hand (see docs/ADR004-app-deployment.md). So this skill runs docs/ADR004-app-deployment.md's manual runbook end-to-end. Do not use the restart verb as a substitute for a deploy — it only rolls pods on the App's existing cached spec.image (see app_controller.go:120); it never rebuilds anything.

This is a genuine build-from-local-disk flow (unlike the old, wrong version of this skill): the image is built from whatever is on disk in $ARGUMENTS's repo path right now, not from origin/main. If you want "latest remote main" instead, git pull --ff-only first.

Step 0 — Confirm scope with the user before touching prod

This SSHes into a live Hetzner node and patches a running App CR — state a one-line plan (repo, app name, target image tag) and get a go-ahead before Step 4 (the actual ctr import + kubectl patch). Steps 1–3 (discovery, build, smoke test) are safe/local and don't need to wait for that confirmation.

Step 1 — Fetch the app-cluster kubeconfig (self-managed, no infra node)

Since the w1/m19.1 pivot there is no mgmt cluster — scripts/fetch-app-kubeconfig.sh discovers a control-plane node via the hcloud API (label caph-cluster-bex) and SSH-fetches /etc/kubernetes/admin.conf:

# from the bex repo root (where this command runs)
set -a; source ./.env; set +a
# default key is ~/.ssh/id_bex (see scripts/fetch-app-kubeconfig.sh); override only if your key is elsewhere
BEX_SSH_KEY_PATH=~/.ssh/id_bex bash scripts/fetch-app-kubeconfig.sh /tmp/bex-app.kubeconfig
export KUBECONFIG=/tmp/bex-app.kubeconfig
kubectl get app <app-name> -o yaml   # baseline: current image, port, generation, revision

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file 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. 6d ago First seen · 90 lines · 58 tokens per session scan A b416593e60eb

Subscribe to this mod's changes

deploy-app-from-local is a skill published in the GitHub repository bex-co/bex (420 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,557 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

argocd-expert

Expert-level ArgoCD GitOps deployment, application management, sync strategies, and production operations. Use when the user mentions GitOps, Kubernetes, continuous deployment, declarative, or automation, or when the task involves ArgoCD Architecture, Application CRD, AppProject, or ApplicationSet.

personamanagmentlayer/pcl · 65 tokens

fluxcd

Operational skill for agents to run GitOps with Flux CD - GitRepository, Kustomization, HelmRelease, image automation, and reconciliation debugging.

alivirgo/Major-AI-Skills · 32 tokens

gh-skill

Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.

cli/cli · 41 tokens

conventional-commit

Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.

JanDeDobbeleer/oh-my-posh · 47 tokens

gh

Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.

cli/cli · 32 tokens

writing-clearly-and-concisely

Apply whenever writing content a human will read — emails, documents, reports, documentation, messages, UI copy, commit messages, explanations, or any other prose. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

JanDeDobbeleer/oh-my-posh · 55 tokens