What is auggie-setup?

A command that guides users through configuring credentials for Auggie, a code-context plugin. It checks login status, starts browser-based login when needed, and explains how to verify access.

Checking Auggie authentication, logging in, verifying the saved token and service address, and restarting Claude Code before indexing a codebase.

It removes guesswork from signing in and making the saved credentials available to the plugin.

auggie-setup — Command by vleytman

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/vleytman/1wp-plugins/auggie-setup

Clone the repo

git clone --depth 1 https://github.com/vleytman/1wp-plugins

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 393 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	$0.00012	$0.00393
Opus 5	$0.00006	$0.00197
Sonnet 5	$0.00002	$0.00079
Haiku 4.5	$0.00001	$0.00039

Measured yesterday against content hash cdb40ae59f3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auggie-setup 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/auggie-context/commands/auggie-setup.md · 69 lines

What it actually says

Auggie Setup Command

Help the user configure their Auggie credentials using auggie login.

Steps to Guide the User

Step 1: Check if already authenticated

Ask the user to run:

auggie token print

If this outputs accessToken and tenantURL, they're already authenticated. Skip to Step 3.

If it shows an error or asks to login, proceed to Step 2.

Step 2: Authenticate with Auggie

Instruct the user:

Install Auggie CLI (if not already installed):

Visit https://docs.augmentcode.com/cli for installation instructions.
Login to Auggie:
```
auggie login
```
This will:
- Open a browser for authentication
- Save credentials to ~/.augment/session.json
- The SDK automatically reads from this file
Verify login succeeded:
```
auggie token print
```
You should see your accessToken and tenantURL.

Step 3: Restart Claude Code

After authenticating, restart Claude Code to pick up the new credentials.

Then run /auggie-index to index your codebase.

How It Works

The Auggie SDK automatically loads credentials from ~/.augment/session.json (created by auggie login). No environment variables or manual configuration needed.

Troubleshooting

"Command not found: auggie"

Install the Auggie CLI from https://docs.augmentcode.com/cli

"Not authenticated" errors

Run auggie login again to refresh your session.

Credentials not being picked up

Verify ~/.augment/session.json exists
Restart Claude Code after logging in

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.

yesterday First seen · 69 lines · 12 tokens per session scan A cdb40ae59f3c

Subscribe to this mod's changes

auggie-setup is a command published in the GitHub repository vleytman/1wp-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 393 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.

Browser automation

auggie-setup