agentmods.dev

ark-adopt

ark-adopt is a skill for Claude Code, Codex from pedroknigge/arkgate. It costs 33 tokens per session (5,827 once invoked), scanned A, original, MIT.

A guided setup for an architecture rules file called ark.config.json. It compares the rules with the project's real folders and records reusable structural patterns.

In plain words
What is it for?
Use it when starting or correcting an Ark-based project structure, defining layers and shared areas, and preparing rules for placing future files.
Why use it?
It helps prevent architecture rules from becoming inaccurate or too strict as the codebase changes. The included CLI checks whether the setup matches the repository.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 1repo changed today A scan 33 tokens original MIT

Good fit Use it when starting or correcting an Ark-based project structure, defining layers and shared areas, and preparing rules for placing future files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedroknigge/arkgate/ark-adopt
View source ↗ pedroknigge/arkgate npmjs.com
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.

Any agent
npx skills add pedroknigge/arkgate --skill ark-adopt
Clone the repo
git clone --depth 1 https://github.com/pedroknigge/arkgate

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 ark-adopt

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-adopt.svg)](https://agentmods.dev/skills/pedroknigge/arkgate/ark-adopt)
Your own site
<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-adopt"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-adopt.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00033 $0.05827
Opus 5 $0.00016 $0.02913
Sonnet 5 $0.00007 $0.01165
Haiku 4.5 $0.00003 $0.00583

Measured today against content hash b624d3ecdf7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ark-adopt 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 today.

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.

templates/agent-skills/ark-adopt/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ark-adopt — Mark the path (session 0)

Contener · Guiar · Ordenar. In plain words: contain the write, guide the next step, order leftover mess. This door is Contener: write the path so the tree has honest houses. Skills never enforce — CLI / hooks / CI do.

When: empty tree, or the rules file does not match the real folders (session 0). Not when: a single new file (/ark-place) or leftover design after the path is honest (/ark-explore then /ark-autopilot).

Steps

  1. Read arkgate-check --doctor (one light, one next action).
  2. Write ark.config.json (and a baseline only for genuine debt) in this turn.
  3. Re-run doctor. Day-to-day new files: /ark-place.

Checklist

  • Existing tree: propose SharedKernel (types/constants) + CompositionRoot (wiring) + src/**/domain/**. Never dump bare src/lib/** into Application.
  • Generate .ark/golden-pattern.json (load-bearing for /ark-place).
  • Future houses: mark unused layer globs reserved / allowEmpty so --strict-config does not fail.
  • When the product map or glossary names a house, write layers[].description as app-context copy (what this folder is in the product). Compact starter may omit. Do not invent captions. Do not invent /ark-describe.
  • CLI-first: if arkgate-check already resolved the root, do not wait on MCP.
  • Do not add arkRun or arkOrder unless the user wants that extra. When they do, write advisory extra in this turn (arkRun schema 1.2+; arkOrder schema 1.3+). Absence is silent and valid. Compact starter stays extras-off. Skills never enforce.

Invoking this skill is the approval. Write the architecture config in this turn. Greenfield: scaffold like --recommend. Brownfield: match product reality, freeze only genuine debt. A green check over a wrong config is a false green.

Autonomy contract

The CLI is a sensor and gate, never the deliverable. CLI budget: one ark-check --recommend or --coverage / --doctor; then write; then ark-check. Forbidden as the result: preview-only adopt, “approve?”, or STOP — invoke /ark-architect / /ark-contract. Do that work here.

Read the full file on GitHub · 329 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. today Changed · +4 lines b624d3ecdf7a
  2. 3d ago Changed · +18 lines 60f1abef551a
  3. 6d ago First seen · 307 lines · 33 tokens per session scan A 9c45b7b3fbb3

Subscribe to this mod's changes

ark-adopt is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 5,827 once invoked, about $0.0002 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.

Claude Codeai-agentsarchitecturedddevent-drivengovernance
Related

Other skills, from other repositories

architecture-patterns

Software architecture patterns and best practices.

aAAaqwq/AGI-Super-Team · 10 tokens

architecture-patterns

Software architecture patterns and best practices.

miles990/claude-software-skills · 10 tokens

architecture-paradigm-event-driven

Applies event-driven async messaging to decouple producers and consumers. Use when designing real-time or multi-subscriber systems needing loose coupling.

athola/claude-night-market · 34 tokens

architecture-paradigm-serverless

Applies serverless FaaS patterns for event-driven workloads. Use when designing bursty workloads with minimal infrastructure and pay-per-execution cost model.

athola/claude-night-market · 37 tokens

data-mesh-expert

Expert-level data mesh architecture, domain-oriented ownership, data products, federated governance, and self-serve platforms. Use when the user mentions architecture, domain driven, data products, governance, or platform, or when the task involves Data Mesh Principles, Domain-Oriented Data Ownership, Data as a…

personamanagmentlayer/pcl · 75 tokens

code-review-architecture

Architecture-focused code review covering hexagonal boundary violations, DDD anti-patterns, CQRS misuse, and microservices coupling issues. Applied in addition to the language-specific review skill when architecture markers are detected. Invoked when reviewing hexagonal architectures, DDD patterns, or microservices…

soulcodex/agentic · 63 tokens