alden

Commands

Run alden <command> --help for the same information in your terminal.

alden auth

Sign in to GitHub.

Command What it does
alden auth login Uses the GitHub CLI's sign-in if there is one. Otherwise signs you in with a code in your browser and stores the token.
alden auth login --device Signs in with a code in your browser, even if the GitHub CLI is signed in.
alden auth login --with-token Reads a token from standard input, e.g. echo $TOKEN | alden auth login --with-token.
alden auth status Shows the account Alden is using, where the token comes from, and its scopes.
alden auth logout Removes the token Alden stored. Doesn't touch the GitHub CLI's sign-in.

Alden looks for a token in this order:

  1. The ALDEN_GITHUB_TOKEN environment variable.
  2. The token Alden stored, in the OS keychain (or, where there's no keychain, a file only you can read).
  3. The GitHub CLI's token (gh auth token).

alden queue

Ranks the open PRs waiting on your review. See The review queue.

Flag What it does
--repo <owner/name> Only this repo. Repeat for more.
--org <name> Only repos in this organisation. Repeat for more.
--limit <n> The most PRs to fetch. Default 100.
--include-drafts Include draft PRs.
--refresh Ignore the 60-second cache.
--json Print the ranked queue as JSON. Schema: packages/schema/json/ranked-queue.v1.json.

alden open

alden open <#>

Opens a PR from your last alden queue in the browser, by its number in that list.

alden review

alden review [pr]

Briefs you on a PR, or on your uncommitted local changes when you don't name one. pr can be a PR URL, owner/repo#123, or a number from your last alden queue. See Briefings and checks.

Flag What it does
--no-llm Run only the deterministic checks, without asking a model.
--no-graph Skip the code graph (callers outside the diff).
--model <name> Use this model for this review, e.g. opus, instead of your configured one.
--effort <level> How hard the model thinks: low, medium, high, xhigh or max. Default: the model's own.
--json Print the briefing as JSON. Schema: packages/schema/json/briefing.v1.json.

Local reviews cover staged, unstaged and untracked files, compared with HEAD.

alden ui

Opens the queue and briefings in your browser, served on 127.0.0.1 only until you stop it. See The web UI.

Flag What it does
--port <n> Serve on this port instead of a free one.
--no-open Print the link instead of opening a browser.

alden doctor

Checks your setup here: the Alden version (and whether a newer one exists), where Alden keeps files, your settings, the GitHub sign-in and its scopes, the model and today's budget, whether this folder is a clone (and of which repo), and which languages the code graph reads in it. Every problem comes with its fix. --json prints the findings as data. Exits with 1 when something fails.

alden stats

Shows a repo's time to first review and review cycle time, before and after Alden.

Flag What it does
--repo <owner/name> The repo (default: the one this clone's origin points at).
--days <n> Look at PRs opened in the last n days. Default 90.
--since <date> Compare before and after this date (YYYY-MM-DD), instead of your first use of Alden.
--horizon <days> Judge each wait over this many days. Default 14.
--refresh Ignore the hour-long cache.
--json Print the stats as JSON. Schema: packages/schema/json/repo-stats.v1.json.

alden feedback

Shows how often you agreed with Alden's flags, and what it missed. --json prints the summary. --export <file> writes your feedback to a file you can share, with repo names, titles, paths and notes removed; add --full to keep them.

alden memory

Lists what Alden has learned about you in a repo, and your notes for it: by default the repo of the clone you're in, or --repo owner/name. --json prints the items. See Learning and memory.

Command What it does
alden memory add <text> Adds a note; the model gets it with every review of the repo.
alden memory forget <id> Forgets a note or a learned item, by the id alden memory shows.

alden telemetry

Anonymous usage stats, off unless you say yes. alden telemetry says whether they're on; on and off change it (off also deletes anything not yet sent); show prints what's waiting to be sent. See Usage stats.

alden spend

Shows what Alden has spent on models today and over recent days, against your caps. --json prints the report as data. See Models, providers and budgets.

alden config

Reads and changes settings. See Configuration.

Command What it does
alden config get <key> Prints a setting, e.g. alden config get model.name.
alden config set <key> <value> Changes a setting in your user config, e.g. alden config set budget.dailyUsd 20.
alden config unset <key> Removes a setting from your user config, so its default applies again, e.g. alden config unset model.effort.
alden config list Prints every setting after merging the defaults, your user config and the repo's config.
alden config path Prints the path of your user config file.