aim-init

aim-init is a command for coding agents from phuonghx/aim-cli. It costs 8 tokens per session (183 once invoked), scanned A, original, MIT.

A workspace setup command for AIM, a tool that stores project guidance, tasks, and agent context in the repository.

In plain words
What is it for?
Use it to initialize AIM, synchronize its context files, read generated project guidelines, and inspect the task list.
Why use it?
It brings an existing project’s rules and backlog into sync so an agent can work with the project’s current context.

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/phuonghx/aim-cli/aim-init
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Wrote 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.

agentmods badge for aim-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuonghx/aim-cli/aim-init.svg)](https://agentmods.dev/commands/phuonghx/aim-cli/aim-init)
Your own site
<a href="https://agentmods.dev/commands/phuonghx/aim-cli/aim-init"><img src="https://agentmods.dev/badge/commands/phuonghx/aim-cli/aim-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 183 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 $0.00008 $0.00183
Opus 5 $0.00004 $0.00092
Sonnet 5 $0.00002 $0.00037
Haiku 4.5 $0.00001 $0.00018

Measured yesterday against content hash c8b7b8595a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aim-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.

aim/templates/commands/aim-init.md · 15 lines

What it actually says

Initialize AIM Workspace

Initialize and synchronize the AIM project workspace context to get up to speed.

Instructions:

  1. Check if the .ai-context directory exists.
  2. If the project is not yet initialized with AIM, run aim init --all-agents in the terminal to initialize all agents non-interactively.
  3. If it is already initialized, or immediately after running aim init, run aim sync to make sure all rule files, modular skills, and command shims are fully synchronized.
  4. Read the generated project guidelines (e.g. CLAUDE.md, ANTIGRAVITY.md, .cursorrules or .cursor/rules/aim.mdc depending on the active editor context).
  5. Check the list of tasks via aim task list to understand the backlog.
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 · 15 lines · 8 tokens per session scan A c8b7b8595a3a

Subscribe to this mod's changes

aim-init is a command published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 183 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 2026-09-03.