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.
git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/agricidaniel/ace-claude-code/init)<a href="https://agentmods.dev/commands/agricidaniel/ace-claude-code/init"><img src="https://agentmods.dev/badge/commands/agricidaniel/ace-claude-code/init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/agricidaniel/ace-claude-code/init"><img src="https://agentmods.dev/badge/commands/agricidaniel/ace-claude-code/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00009 | $0.01361 |
| Opus 5.5 | $0.00004 | $0.00544 |
| Sonnet 5.5 | $0.00002 | $0.00272 |
| Haiku 4.5 | $0.00001 | $0.00136 |
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 1mo 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.
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
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.
- 1mo ago First seen · 244 lines · 9 tokens per session scan A 4559483807fc
ace:init is a command published in the GitHub repository AgriciDaniel/ace-claude-code (27 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 1,361 once invoked, about $0.0000 per session on Opus 5.5. 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.