init

A setup command for Agent Driven Development, a way to organize software work around written project information and checks. It interviews the team and creates the framework needed for a new or existing project.

In plain words
What is it for?
Use it to initialize a project, quickly set up a prototype, reconfigure an existing setup, run headlessly in automation, or synchronize the project registry.
Why use it?
It avoids having to configure the development process from scratch and supports both interactive and fully automated setup.

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/mountainunicorn/add/init
Any agent
npx skills add MountainUnicorn/add --skill init
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,623 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 $0.00018 $0.07623
Opus 5 $0.00009 $0.03811
Sonnet 5 $0.00004 $0.01525
Haiku 4.5 $0.00002 $0.00762

Measured 2d ago against content hash ea32d5ee2c45, 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.

core/skills/init/SKILL.md · 646 lines

How it starts

The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Init Command v{{VERSION}}

Initialize Agent Driven Development for this project. This command conducts a structured interview to understand the project, then scaffolds the full ADD framework.

Modes

Flag Purpose Questions Target user
(none) Full interview — detects adoption vs greenfield, runs Phases 0-5 ~12 New projects with non-trivial scope or existing codebases
--quick Greenfield fast path — 5 essential questions, sensible defaults elsewhere 5 Prototypes, solo projects, time-constrained onboarding
--defaults True non-interactive init — every value derived or defaulted, zero questions 0 Headless sessions (claude -p, codex exec), CI pipelines
--reconfigure Re-run interview preserving existing answers as defaults ~12 Updating an already-initialized project
--sync-registry Read-only: reconcile ~/.claude/add/projects/{name}.json with ground truth 0 Fixing drift detected by the registry-sync rule

Quick Mode (--quick)

Greenfield fast path. Skips adoption detection, skips profile-derived questions, and defaults anything that isn't one of the 5 essential answers. Use when you want ADD initialized in ~2 minutes.

The 5 questions

  1. Name — "Project name? (defaults to directory basename: {current_dir_name})"
  2. Languages / frameworks — "What's the primary stack? (e.g., 'python+fastapi', 'typescript+react', 'go', 'rust+axum')"
  3. Environment tier — "Deployment scope: 1 (local only), 2 (local + prod), or 3 (local + dev + staging + prod)? (default: 2)"
  4. Maturity — "Project maturity: poc, alpha, beta, or ga? (default: alpha)"
  5. Autonomy — "Agent autonomy level: guided (ask often), balanced (default), or autonomous (trust)? (default: balanced)"

Defaults applied

Everything else that the full interview asks is defaulted:

Area Quick-mode default
PRD depth 1-pager generated from (name, stack, scope-paragraph prompt)
Quality mode strict for beta/ga, standard for alpha, spike for poc
CI/CD provider Inferred from .github/ if present, otherwise none
Commit convention Conventional commits
Protected branches [main]
Coverage threshold 80% at beta/ga, 50% at alpha, 0 at poc
Branding palette Default ADD raspberry (#b00149) until /add:brand is run
Image generation enabled: false, nudged: false

Read the full file on GitHub · 646 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 · 646 lines · 18 tokens per session scan A ea32d5ee2c45

Subscribe to this mod's changes

init is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 7,623 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 2026-08-30.