A command for managing a project's development server, including starting it, stopping it, viewing logs, listing servers, and opening the app.

Use it to start a healthy local server, get its access URL, inspect live logs, stop it, list running servers, or open the app in a browser.

It allocates a separate port and proxy address for each agent, reducing conflicts when several development environments run at once.

ads — Command by jayvee

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/jayvee/aigon/ads

Clone the repo

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

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 574 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	$0.00017	$0.00574
Opus 5	$0.00009	$0.00287
Sonnet 5	$0.00003	$0.00115
Haiku 4.5	$0.00002	$0.00057

Measured 2d ago against content hash 39e954235bd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ads 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 2d 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.

.claude/commands/ads.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aigon-dev-server

Manage the dev server for the current project. Handles port allocation, process lifecycle, proxy registration, and log viewing.

CRITICAL: NEVER run the project's dev command directly. ALWAYS use aigon dev-server start. Running the dev command directly bypasses port allocation and will cause port conflicts in worktrees.

Usage

Run the appropriate subcommand based on what's needed:

Start the dev server

aigon dev-server start

This will:

Allocate a unique port (each agent gets its own offset from the project's base port)
Start the dev server process in the background with PORT=<allocated>
Register with the local proxy for a custom subdomain URL (e.g. http://cx-121.myapp.test)
Wait for the server to become healthy
Print the URL to access the app — always use this URL

Check dev server logs

aigon dev-server logs

Use -f to follow logs in real time:

aigon dev-server logs -f

Stop the dev server

aigon dev-server stop

List all running dev servers

aigon dev-server list

Open in browser

aigon dev-server open

Opens the dev server URL in the default browser. Uses the proxy subdomain URL if available, otherwise falls back to localhost.

You can also auto-open when starting the server:

aigon dev-server start --open

Get the URL for the current context

aigon dev-server url

Prints the proxy subdomain URL (or localhost fallback) for use in testing and browser access.

Notes

The dev server command is read from devProxy.command in .aigon/config.json (set this to whatever the project uses)
Port is allocated automatically — agents get offsets from the base port (cc=+1, ag=+2, cx=+3, cu=+4)
The base port is configured per-project in .aigon/config.json (devProxy.basePort). Worktree agents get offsets from this.
If the proxy is running (aigon proxy install), the server gets a named URL like http://cx-121.myapp.localhost
Without the proxy, it falls back to http://localhost:<port>
Use aigon dev-server logs to diagnose startup issues — all stdout/stderr is captured
To check what's running: aigon dev-server list shows all active servers with their ports and URLs

Read the full file on GitHub · 82 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.

2d ago First seen · 82 lines · 17 tokens per session scan A 39e954235bd6

Subscribe to this mod's changes

ads is a command published in the GitHub repository jayvee/aigon (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 574 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.

Browser automation agent-orchestration ai-agents claude-code cli codex developer-tools

browser

Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden. Tabs in this worker share an ephemeral browser profile, while…

Untrivial-ai/agent-orchestrator · 0 tokens

ads