A command that quickly starts a new software project with planning documents and sensible defaults. It detects the project type from files such as package.json, Cargo.toml, or pyproject.toml and prepares a roadmap.

Use it to initialize project planning, create a project description and roadmap, detect the technology stack, and check whether an existing project plan should be reinitialized.

It removes repetitive setup when beginning a project. It also spots common project structures, including a monorepo, which is one repository containing multiple related applications or packages.

ace:init — Command by AgriciDaniel

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/agricidaniel/ace-claude-code/init

Clone the repo

git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,361 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.

Model	Per session	Once invoked
Fable 5	$0.00009	$0.01361
Opus 5	$0.00005	$0.00681
Sonnet 5	$0.00002	$0.00272
Haiku 4.5	$0.00001	$0.00136

Measured 2d ago against content hash 4559483807fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace: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.

.ace/commands/init.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Combines /ace:new-project + /ace:create-roadmap into a single fast command. Go from zero to ready-to-plan in one step.

Templates: @.ace/templates/planning/project.md @.ace/templates/planning/roadmap.md @.ace/templates/planning/state.md

Check for:

Existing PROJECT.md (offer to reinitialize)
package.json, Cargo.toml, pyproject.toml (detect project type)
.ace/planning/codebase/ (existing analysis)

0. Pre-Flight Check

if .ace/planning/PROJECT.md exists:
    Ask: "Project already exists. Reinitialize? (y/n)"
    if no: EXIT with /ace:status suggestion

1. Auto-Detect Project Type

Scan for indicators:
- package.json with "next" -> frontend/fullstack
- package.json with "express" or "fastify" -> backend
- package.json with "react" only -> frontend
- Cargo.toml -> backend (Rust)
- pyproject.toml -> backend (Python)
- mcp/agent patterns -> agentic
- multiple package.json files -> monorepo
- tsconfig with "lib" -> library

If detected:
    projectType = [detected]
    Display: "Detected project type: [type]"
else:
    projectType = "fullstack" (default)

2. Quick Questions (Minimal)

if $ARGUMENTS is empty:
    Ask: "Project name?"
else:
    projectName = $ARGUMENTS

Ask: "One sentence - what does this project do?"
    -> coreValue

That's it for questions. Everything else uses smart defaults.

3. Generate PROJECT.md

Create .ace/planning/PROJECT.md:

# [Project Name]

## Core Value
[coreValue from question]

## Overview
[Auto-generated based on project type and coreValue]

## Requirements

### Must Have
- Core functionality based on project type
- (To be refined during planning)

### Should Have
- (To be defined)

### Nice to Have
- (To be defined)

## Technical Stack
[Auto-filled from detected files or project type defaults]

## Constraints
- (None specified - to be added as discovered)

## Success Criteria
- Project successfully delivers core value
- All must-have requirements implemented
- Quality gates pass

Read the full file on GitHub · 244 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.

2d ago First seen · 244 lines · 9 tokens per session scan A 4559483807fc

Subscribe to this mod's changes

ace:init is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 1,361 once invoked, about $0.0000 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.

Planning ai claude-code claude-code-skill developer-tools open-source

ace:init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

0. Pre-Flight Check

1. Auto-Detect Project Type

2. Quick Questions (Minimal)

3. Generate PROJECT.md

What this file has done since we first saw it

Other commands, from other repositories

canvas

document

review

test

fix-issue

migrate