external-app-create

A generate-only skill that creates the files for a Cozystack external app package, including its Helm chart and GitOps registration.

In plain words
What is it for?
Use it to scaffold a deployable external app package and its platform registration; it does not apply changes to a cluster, commit, or push.
Why use it?
It removes the repetitive setup needed to make an external app appear in the Cozystack dashboard and deployment pipeline while leaving cluster changes under the user's control.

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/cozystack/ccp/external-app-create
Any agent
npx skills add cozystack/ccp --skill external-app-create
Clone the repo
git clone --depth 1 https://github.com/cozystack/ccp

Made for: Claude Code, Codex.

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,797 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 $0.00127 $0.15797
Opus 5 $0.00063 $0.07898
Sonnet 5 $0.00025 $0.03159
Haiku 4.5 $0.00013 $0.01580

Measured yesterday against content hash 04f336255685, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

external-app-create 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 yesterday.

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.

plugins/cozystack/skills/external-app-create/SKILL.md · 1,274 lines

How it starts

The opening of the file, as written. The whole thing — 1,274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cozystack:external-app-create

This skill scaffolds a new Cozystack external app package. It creates all files needed for the app to appear in the Cozystack dashboard and be deployable via the GitOps pipeline (GitRepository → Flux HelmRelease → ApplicationDefinition).

This is a generate-only skill. It never applies anything to a cluster, never commits, and never pushes. The user handles git operations themselves.

Work in reasoning mode. Follow the phases in order. When a step fails or is ambiguous, stop and ask — do not guess API shapes or secret names.

Use the phrasing "cozystack:external-app-create" (not "the skill") in messages to the user, and state progress at each phase boundary.

Match the operator's natural language detected from prior conversation messages — use it in prompts, AskUserQuestion options, summaries, and gates. Generated Helm template files, ApplicationDefinition values, and any text destined for git or the cozystack dashboard stay in their canonical form (usually English) per cozystack's public-content rules.

Phase 1 — Parse arguments

$ARGUMENTS contains the free-form tail after /cozystack:external-app-create. Extract:

  • Positional <app-name> — lowercase, hyphen-separated (e.g., immich, my-app). Required.
  • --depends-on=<list> — comma-separated dependency names (e.g., postgres, redis). Default: none.
  • --operator=<url> — Helm chart repository URL for a required operator (e.g., https://immich-app.github.io/immich-charts). Default: none.
  • --repo-dir=<path> — path to the external-apps repository root. Default: current working directory.

If <app-name> is missing, use AskUserQuestion to ask for it.

Phase 2 — Pre-flight checks

Bail early if any check fails.

  1. Repository structure: verify $REPO_DIR contains init.yaml, packages/core/platform/Chart.yaml, scripts/package.mk, and the five platform template files packages/core/platform/templates/{namespaces,helmrepositories,helmreleases,helmcharts,cozyrds}.yaml. If any are missing, tell the user to cd into the external-apps repo root or pass --repo-dir — Phase 8 appends to all five.
  2. Tools installed: check that yq (v4), jq, base64, helm, and cozyvalues-gen are available via command -v. If cozyvalues-gen is missing, print:
    cozyvalues-gen is required. Install it from:
    https://github.com/cozystack/cozyvalues-gen/releases/latest
    
    Do not install it automatically. Stop.
  3. No collision: verify packages/apps/$APP_NAME/ does not already exist. If it does, stop and ask the user whether to overwrite or pick a different name.
  4. Cozystack contract resolution source: Phase 4 Step 2 needs to read packages/system/<dep>-rd/cozyrds/<dep>.yaml from cozystack. Detect the best available source in this order and record it as $COZYSTACK_CONTRACT_SOURCE:
    • local$COZYSTACK_REPO is set and points at a cozystack checkout containing packages/system/. Fastest, works offline.
    • githubgh CLI is authenticated (gh auth status succeeds). Resolves against cozystack/cozystack@main.
    • clusterkubectl config current-context succeeds and the target context is a cozystack cluster. Authoritative for that cluster version; read-only.

Read the full file on GitHub · 1,274 lines

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. yesterday First seen · 1,274 lines · 127 tokens per session scan A 04f336255685

Subscribe to this mod's changes

external-app-create is a skill published in the GitHub repository cozystack/ccp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 127 tokens to every session and 15,797 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens