init

A repository setup command that adds instructions and skills for coding agents, plus optional development and quality checks.

In plain words
What is it for?
Use it to initialize a new or existing codebase with AGENTS.md, a CLAUDE.md bridge, agent skills, language rules, and optional full tooling.
Why use it?
It gives agents consistent project guidance and can add hooks, a development container, continuous-integration checks, and baseline updates without replacing existing setup.

Command

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 commands/vyuh-labs/dxkit/init
Clone the repo
git clone --depth 1 https://github.com/vyuh-labs/dxkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,906 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 $0.00000 $0.01906
Opus 5 $0.00000 $0.00953
Sonnet 5 $0.00000 $0.00381
Haiku 4.5 $0.00000 $0.00191

Measured 2d ago against content hash 21add7d49dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 2d 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.

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.

docs/commands/init.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vyuh-dxkit init

Canonical first install: npm init @vyuhlabs/dxkit — collapses install + scaffold into a single command. Falls through to vyuh-dxkit init --full --yes internally.

Direct use: vyuh-dxkit <cmd> after npm install -g @vyuhlabs/dxkit, or npx vyuh-dxkit <cmd> for one-shot use. Examples on this page use the short form.

Install the dxkit agent DX layer in a repository: AGENTS.md + CLAUDE.md shim + .claude/skills/dxkit-*/ (the lifecycle skills)

  • .claude/rules/ (per-language conventions), plus — optionally — git hooks, per-stack devcontainer, CI guardrails, and the post-merge baseline-refresh workflow.

Works on any codebase, greenfield or brownfield. dxkit is additive: existing .husky/, .devcontainer/, or CI workflows are never destroyed — sidecars are written instead (see "Additive install" below).

Usage

vyuh-dxkit init [options]

Modes

Mode Effect
--dx-only (default) Agent DX layer only — AGENTS.md, CLAUDE.md, .claude/skills/dxkit-*/, .claude/rules/, .vyuh-dxkit.json
--full Agent DX + git hooks + per-stack devcontainer + CI guardrails + baseline-refresh (every --with-* flag enabled)

Options

Option Effect
--with-dxkit-agents Install the dxkit-* skills + AGENTS.md + CLAUDE.md shim. Default-on under --full; opt-in on bare init.
--with-hooks Install .githooks/pre-push for guardrail check. Hook activation is auto-chained via package.json postinstall — teammates who npm install get hooks wired automatically. Pre-commit is opt-in (--with-precommit-hook).
--with-precommit-hook Additionally install .githooks/pre-commit. Implies --with-hooks. Use on small/fast repos where every-commit gating is worth the wait.
--with-devcontainer Install .devcontainer/ with per-stack pinned toolchains (only the languages your project uses) + Claude Code & Codex CLIs
--with-ci Install .github/workflows/dxkit-guardrails.yml (PR-gate). On a stack that declares a capability the ubuntu runner can't serve (e.g. a net*-windows build), also generates a dxkit-gate-<host>.yml job — mark it a required PR check alongside dxkit-guardrails
--with-baseline-refresh Install .github/workflows/dxkit-baseline-refresh.yml (post-merge auto-regen)
--with-pr-review Install .github/workflows/pr-review.yml — Claude Code reviews each PR and posts a comment. Inert until you set the ANTHROPIC_API_KEY repo secret AND ENABLE_AI_REVIEW=true repo variable. Not included in --full because it requires API-cost opt-in.
--detect Auto-detect stack (language, framework); skip most prompts
--yes Accept all defaults
--force Overwrite existing files in place (otherwise sidecars are emitted — see "Additive install" below)
--stealth Generated files are gitignored — local-only, not committed
--name <n> Override the project name
--no-finish Opt out of the auto tools-install + baseline capture — arm the gates now, run vyuh-dxkit tools install / vyuh-dxkit baseline create later
--no-scan Skip the codebase analysis step

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 0 tokens per session scan A 21add7d49dba

Subscribe to this mod's changes

init is a command published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,906 tokens. 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.