ctoc

CTO Chief
The CTO your AI never had.

CTO Chief is a Claude Code plugin that turns AI coding from "generate and pray" into disciplined engineering. Every feature follows a 16-step Iron Loop — plan before code, test before ship, secure before deploy — wrapped by a refinement loop that drives findings (warnings included) to zero before you ever see the result. 110 agents across 22 categories route through a 4-tier architecture (CTO Chief → sub-orchestrators → specialists → Haiku scouts), with 4 mandatory human gates. The 421-file skill library (99 Tier-2 specialist bodies + 322 reference files) has been brought to 2026 best-practices quality through a websearch → update → critique → update loop on every specialist — no invented statistics, sourced citations, 7-language coverage. The result: AI that writes production-quality code on the first try.

Install

/plugin marketplace add https://github.com/robotijn/ctoc
/plugin install ctoc

[!TIP] Enable auto-update: /plugin → Marketplaces tab → robotijn → Enable auto-update

Quick Start

1. Start Claude Code:

claude

2. Open the dashboard:

/ctoc

That's it. CTO Chief detects your stack and shows a dashboard.

3. Tell Claude what you want to build:

I want a SaaS product with AI to help creative writers when they get stuck

CTO Chief starts with ideation — agents explore your idea with you, ask clarifying questions, and shape it into actionable plans. Steps 1-7 are collaborative: agents ask, you decide. Steps 8-16 are automated: agents execute, you review the result. Use numbered menus ([1], [2], [3]) to navigate.

Already know exactly what you want? Just be specific: "Add a /health endpoint returning 200 OK" — CTO Chief skips ideation and goes straight to planning.

[!NOTE] CTO Chief is open source and actively developed. Issues, PRs, and skill improvement suggestions are welcome.

[!TIP] For autonomous agent workflows, use claude --dangerously-skip-permissions to avoid repeated tool-call prompts. This is safe on feature branches where git can revert changes. Add --continue to resume a previous session.

---

Auto-Availability After Install

When you install CTOC from the marketplace, Claude Code auto-discovers every artifact the plugin ships — slash commands, agents, hooks, and skills — per the Claude Code Plugins reference. No manual wiring is needed. The 99 Tier-2 specialist SKILL.md files then become available through three routing paths:

1. Slash-command pipeline — /ctoc (or any sub-command) dispatches CTO Chief, which dispatches a Tier-1 sub-orchestrator, which dispatches the relevant Tier-2 specialist by name. This is the path used during the Iron Loop and refinement loop.
2. when_to_load trigger phrases — each SKILL.md declares a list of natural-language triggers in YAML frontmatter (e.g. "SBOM", "prompt injection", "NIST 800-61"). When your conversation matches a trigger, Claude Code auto-loads the skill into context with no slash command needed.
3. Direct Skill tool invocation — Claude can invoke any skill explicitly via the built-in Skill tool (e.g. Skill(skill_name="ctoc:llm-security-tester")) based on conversational context.

The auto-discovery is documented behavior of Claude Code's plugin system. Installing CTOC therefore makes the entire 421-file library reachable without configuration — you only pay for what loads, but everything is wired and ready.

---

Skill Library Quality Bar

Every one of the 99 Tier-2 specialist SKILL.md bodies was brought to 2026 best-practices quality through an explicit improvement loop (v6.9.15–v6.9.27). The library is not a grab-bag of LLM-generated stubs — it is engineered.