init

A setup command that creates a central .ai/ configuration directory and imports settings from AI coding tools already found in the project.

In plain words
What is it for?
Use it when first adopting the configuration system, to detect existing tool settings, import them, and prepare files for later synchronisation.
Why use it?
It gives a project one place for its AI instructions instead of leaving them scattered across tool-specific files.

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/thethoughtagen/agentsync/init
Clone the repo
git clone --depth 1 https://github.com/TheThoughtagen/agentsync
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 289 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 $0.00013 $0.00289
Opus 5 $0.00006 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured yesterday against content hash e1fa8df73bd1, 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 yesterday.

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.

plugins/aisync/commands/init.md · 30 lines

What it actually says

/aisync:init

Run aisync init to set up the canonical .ai/ directory structure and import existing tool configurations.

Usage

  1. Run the command:

    aisync init
    
  2. Report the results to the user:

    • Which AI tools were detected in the project (Claude Code, Cursor, OpenCode)
    • Which existing configs were imported into .ai/ (e.g., existing CLAUDE.md content imported into .ai/instructions.md)
    • What new files and directories were created
  3. If .ai/ already exists, warn the user before proceeding:

    The .ai/ directory already exists. Running aisync init again may overwrite imported content. Use /aisync:status to check current state instead, or pass --force if you really want to re-initialize.

Notes

  • This is typically run once when first adopting aisync in a project.
  • Detection looks for .claude/, .cursor/, .opencode/, CLAUDE.md, AGENTS.md, and similar tool-native files.
  • After init, run /aisync:sync to propagate the canonical config back to all tools.
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. yesterday First seen · 30 lines · 13 tokens per session scan A e1fa8df73bd1

Subscribe to this mod's changes

init is a command published in the GitHub repository TheThoughtagen/agentsync (2 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 289 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 2026-08-31.