Skip to content
Guardix Guardix

CLI and agent skills

The Guardix CLI (guardix) connects your terminal — or a coding agent — to the same audits and findings you see in the web app. Guardix also ships agent skills that teach tools like Claude Code how to read results, start audits, and compare reports from multiple providers.

Terminal window
curl -fsSL https://github.com/guardixdev/guardix/releases/latest/download/install.sh | sh

The installer picks the right binary, verifies checksums, and places guardix on your PATH (typically /usr/local/bin or ~/.local/bin).

Pin a version or custom install directory:

Terminal window
curl -fsSL https://github.com/guardixdev/guardix/releases/latest/download/install.sh | GUARDIX_VERSION=v0.3.4 sh
curl -fsSL https://github.com/guardixdev/guardix/releases/latest/download/install.sh | GUARDIX_INSTALL_DIR="$HOME/bin" sh

Download a release archive from github.com/guardixdev/guardix/releases, extract, and add the guardix binary to your PATH.

Terminal window
guardix --version
guardix doctor
Terminal window
guardix auth login

The CLI prints a URL (for example https://guardix.io/cli/auth?s=…) and opens your browser. Sign in with GitHub or Google if needed, approve the pairing, and the CLI stores a key locally. The approval page also has a Deny button if the request isn’t yours. Revoke CLI keys anytime under User menu → API keys in the app.

Coding agents and remote shells can’t open a browser. From CLI 0.3.4 onward:

Terminal window
guardix auth login --no-browser --json

--no-browser prints the verification URL instead of opening a browser, and --json emits machine-readable status lines:

{"status":"awaiting_approval","verification_url":"https://guardix.io/cli/auth?s=…","user_code":"…"}
{"status":"authenticated"}

The agent relays the verification_url to you; open it in any browser, confirm the code matches, and Approve (or Deny) the pairing. When approved, the CLI emits {"status":"authenticated"} and stores the key. --json also implies --non-interactive, so the command never prompts.

Terminal window
guardix auth login --api-key gdx_ak_...

Or set GUARDIX_API_KEY in the environment. See API keys for creating keys in the dashboard.

Check status:

Terminal window
guardix auth status

Inside a connected git checkout, many commands infer the repository from git remote:

Terminal window
guardix status # latest audit summary + open findings
guardix finding list # findings for the latest audit
guardix finding get VAU-3 # one finding by short code
guardix audit start --ref main # start a full audit
guardix audit wait --audit '#2' # block until completion (CI-friendly)

Add --json for machine-readable output (it also implies --non-interactive, so commands never prompt). Run guardix manifest --quiet for the full command surface — do not guess flag names.

Useful audit flags mirror the web wizard: --contract (repeatable scope), --doc-url, --doc-text, --doc-file, and --include-repo-docs.

The CLI never handles card data. Paying for a full audit is:

Terminal window
guardix audit start # opens Stripe checkout if needed and waits until you pay
guardix audit start --wait # then keep watching until the audit finishes
guardix billing portal --open # invoices and saved payment methods after the first payment
guardix quota # free-audit remaining + per-audit price

billing portal is available after the first payment (Stripe returns 409 until then). Release Audits that need payment or intake action exit wait with code 3 and print the checkout URL instead of holding.

The Guardix CLI plugin bundles three skills for coding agents:

SkillUse when
guardixReading audit results — status, findings, finding codes like VAU-3, review state.
running-auditsStarting and monitoring audits (audit start, wait, get, logs).
cross-audit-triageComparing findings from multiple sources (Guardix + external firm reports or tool output), correlating duplicates, and adjudicating true vs false positives locally.

From inside Claude Code:

Terminal window
/plugin marketplace add guardixdev/guardix
/plugin install guardix-cli@guardix

Or from a regular shell (scripts, CI):

Terminal window
claude plugin marketplace add guardixdev/guardix
claude plugin install guardix-cli@guardix

Skills live in the plugin package; each skill file describes when the agent should invoke it and which CLI commands to run. Agents should prefer guardix manifest over inventing flags. The same three skills also work in Cursor, which auto-loads agent skills from its skills directories (.cursor/skills/, ~/.cursor/skills/) as well as compatibility paths like ~/.claude/skills.

The cross-audit-triage skill expects report files plus a checkout of the audited commit on disk so findings can be validated against real source. It produces a comparison matrix and optional cross-audit-triage.json artifact. You can sync adjudications back with guardix finding review when ready.

Terminal window
guardix team list
guardix team switch <team-slug>

The active team filters which repositories and audits are visible — match the workspace you use in the browser.