aigon-feature-open

aigon-feature-open is a command for Claude Code, Cursor from jayvee/aigon. It costs 0 tokens per session (457 once invoked), scanned A, a copy of afo, Apache-2.0.

A command that opens a feature worktree in a terminal and starts an AI coding agent to implement it. A worktree is a separate checkout of the repository for isolated changes.

In plain words
What is it for?
Use it to open the newest or a selected feature worktree and start Claude Code, Cursor, Antigravity, or Codex with the corresponding launch settings.
Why use it?
It removes the manual steps of finding the right worktree, opening a terminal, and launching the chosen agent.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md). Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to open the newest or a selected feature worktree and start Claude Code, Cursor, Antigravity, or Codex with the corresponding launch settings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jayvee/aigon/aigon-feature-open
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.

Clone the repo
git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code, Cursor.

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 aigon-feature-open

README.md
[![agentmods](https://agentmods.dev/badge/commands/jayvee/aigon/aigon-feature-open.svg)](https://agentmods.dev/commands/jayvee/aigon/aigon-feature-open)
Your own site
<a href="https://agentmods.dev/commands/jayvee/aigon/aigon-feature-open"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/aigon-feature-open.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 98% copy Near-identical to another mod 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 5.1 $0.00000 $0.00457
Opus 5 $0.00000 $0.00229
Sonnet 5 $0.00000 $0.00091
Haiku 4.5 $0.00000 $0.00046

Measured 3d ago against content hash 16493fe95a1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aigon-feature-open 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.

Origin

This is a copy

98% identical to afo — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/commands/aigon-feature-open.md · 54 lines

What it actually says

feature-open

Open a feature worktree in terminal and automatically start the AI agent with /aigon-feature-do.

Usage

/aigon-feature-open [feature-id] [agent-code]
  • /aigon-feature-open — open the most recently created worktree
  • /aigon-feature-open 77 — open any worktree for feature 77
  • /aigon-feature-open 77 cx — open specifically the cx (Codex) worktree for feature 77

Agent Mappings

Code Agent Command Mode
cc Claude Code claude --permission-mode acceptEdits Auto-edits, prompts for risky Bash
cu Cursor agent --force Auto-approves commands (yolo mode)
ag Antigravity agy --dangerously-skip-permissions Auto-approves all
cx Codex codex --full-auto Workspace-write, smart approval

Safe in worktrees since you can always git reset --hard.

Permission Tips

When an agent asks for permission, here's how to quickly allow:

Agent Allow once Allow always Toggle full-auto
Claude Code Press Enter at prompt Choose "Always allow" at prompt Shift+Tab cycles modes
Cursor Click "Run" Click "Add to allowlist" Enable YOLO in settings
Codex Approve at prompt "Allow and remember" (session) /mode command

Step 1: Run the CLI command

aigon feature-open <args>

This will:

  1. Find the matching worktree
  2. Create a Warp launch configuration
  3. Open Warp with the worktree directory
  4. Auto-run the agent CLI with /aigon-feature-do <ID>

Step 2: Confirm to user

Tell the user:

  • Which worktree was opened
  • Which agent was launched with which feature ID
  • That the agent should start implementing automatically
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. 3d ago First seen · 54 lines · 0 tokens per session scan A 16493fe95a1d

Subscribe to this mod's changes

aigon-feature-open is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 457 tokens. A static security scan graded it A with 0 findings. It is 98% identical to afo, differing in 18 lines, and is treated as a copy.