What is ace:new-project?

A project-setup command that creates or updates PROJECT.md, a file describing the project's purpose and requirements. It can also inspect existing planning files and initialize Git when configured to do so.

Use it when beginning a project to capture its value, overview, and requirements, check existing ACE planning state, and optionally create the initial Git repository commit.

It gives later coding work a shared project specification and establishes planning and version-control setup at the start.

ace:new-project — 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/new-project

Clone the repo

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

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 657 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	$0.00011	$0.00657
Opus 5	$0.00005	$0.00329
Sonnet 5	$0.00002	$0.00131
Haiku 4.5	$0.00001	$0.00066

Measured 3d ago against content hash 4ecaed30a0a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:new-project 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 3d 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/new-project.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This establishes the project specification that guides all subsequent work.

Check for existing project:

If .ace/planning/PROJECT.md exists, offer to update or skip
If .ace/planning/codebase/ exists, use it to inform questioning

Load templates: @.ace/templates/planning/project.md

0. Pre-Flight: Git Initialization

Read config.json for git.enabled and git.autoInit

if git.enabled AND git.autoInit:
    Check if .git directory exists
    if not exists:
        Run: git init
        Run: git add .ace/ CLAUDE.md .gitignore
        Run: git commit -m "chore: initialize ace orchestration system"
        Display: "Git repository initialized"

This ensures all projects have version control from the start.

1. Check Existing State

if .ace/planning/PROJECT.md exists:
    Ask: "PROJECT.md already exists. Update it or skip?"
    Options: "Update existing" / "Skip to /ace:create-roadmap"

2. Gather Project Information

Use AskUserQuestion to extract:

Core Value

"What is the ONE primary value this project delivers?"

Keep to one sentence
Focus on user benefit

Overview

"Describe what you're building and why (2-3 sentences)"

Requirements

"What are the must-have features? (List 3-5)"

For each must-have, ask: "Any should-have or nice-to-have features?"

Technical Stack

If codebase/ exists, pre-fill from STACK.md Otherwise ask: "What's your preferred tech stack?"

Framework (Next.js, React, Express, etc.)
Language (TypeScript, JavaScript)
Database (PostgreSQL, MongoDB, SQLite)
Styling (Tailwind, CSS Modules, etc.)

Constraints

"Any constraints I should know about?"

Time constraints
Technical limitations
Compatibility requirements

Success Criteria

"How will you know this project is successful?"

3. Create PROJECT.md

Write to .ace/planning/PROJECT.md using template.

Read the full file on GitHub · 120 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.

3d ago First seen · 120 lines · 11 tokens per session scan A 4ecaed30a0a1

Subscribe to this mod's changes

ace:new-project is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 657 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.

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

ace:new-project

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

0. Pre-Flight: Git Initialization

1. Check Existing State

2. Gather Project Information

Core Value

Overview

Requirements

Technical Stack

Constraints

Success Criteria

3. Create PROJECT.md

What this file has done since we first saw it

Other commands, from other repositories

canvas

document

test

review

fix-issue

migrate