ark-think

ark-think is a skill for Claude Code, Codex from pedroknigge/arkgate. It costs 28 tokens per session (2,762 once invoked), scanned A, original, MIT.

A guided architecture decision tool for projects using Ark import rules. Software architecture is the way a project's code is divided and connected.

In plain words
What is it for?
It is for reasoning about import rules, module boundaries, ports, and where new code should be placed.
Why use it?
It helps compare a small number of design choices before code is changed, while keeping the final checks deterministic.

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/pedroknigge/arkgate/ark-think
Any agent
npx skills add pedroknigge/arkgate --skill ark-think
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-think

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-think.svg)](https://agentmods.dev/skills/pedroknigge/arkgate/ark-think)
Your own site
<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-think"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-think.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,762 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 $0.00028 $0.02762
Opus 5 $0.00014 $0.01381
Sonnet 5 $0.00006 $0.00552
Haiku 4.5 $0.00003 $0.00276

Measured yesterday against content hash c855495faf3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ark-think 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.

templates/agent-skills/ark-think/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ark-think — Architectural reasoning (host LLM only)

Not a first-run door. One decision only. Session 0 → /ark-adopt. Full map → /ark-explore. Apply → /ark-autopilot. Do not send the user to leftover /ark-contract or /ark-fix.

You are the user's architecture thinking partner inside the project's Ark contract. This skill does not call any LLM API from the arkgate package. You (the host agent) reason; the write-gate and CI remain deterministic.

Improvement compass (process preflight)

When doctor is available, read doctor.improvementCompass (or the human Improvement compass section). Name 1–3 residual lenses in plain language before skill-shopping. Always notAScore — never invent 0–10 scores or Excellent/Good ranks.

What the user should feel next: fewer blocked AI writes, clearer folders, safer domain — then jargon.

Anti false-done: empty plan A + residual lenses / design-weak → Incomplete? yes. Green edges alone are not “architecture finished.”

AI-easy architecture: ports over concrete I/O in domain; one concern per module; golden pattern for new files; place before write (/ark-place / prepare-write).

Out of scope (honest): scalability/performance, full app-security tooling (SAST), and full resilience patterns are out-of-scope lenses — say so; do not invent Ark enforcement for them.

2–3 options labeled by lens impact (what residual improves / what stays out-of-scope).

Deep modules (process)

  • Prefer deep modules (small interface, hidden complexity). Never invent a depth score.
  • Label the seam on each option that introduces a port/adapter; apply the deletion test before pass-through extracts “for testability.”
  • Recommend tests at the public interface of the chosen seam.

When / not when

Use /ark-think when… Do not use it when…
One decision: new layer vs slice, port vs shared, peerIsolation choice Full map / ranked residual / dual-plan seed → /ark-explore
2–3 options already bounded by a known surface Apply remediation → /ark-autopilot
Trade-offs before writing a new feature Brownfield config wrong / false-green → /ark-adopt
Explain why a rule exists in this tree HTML tour → /ark-explain; fitness numbers → /ark-coverage

Read the full file on GitHub · 171 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 Changed c855495faf3e
  2. 5d ago First seen · 171 lines · 28 tokens per session scan A 267d44f2f058

Subscribe to this mod's changes

ark-think is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 2,762 once invoked, about $0.0001 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.