guide · Claude Code
Set up ShipGuard in Claude Code
One sentence is all Claude Code needs. It installs ShipGuard, runs a first scan, keeps the reports on your machine and adds a hook. You approve the sign-in once.
Paste this to your agent
Set up ShipGuard from agenticcli.dev in this repo. Run a first scan, keep the reports locally, and add it as a hook so it runs automatically before every merge.
Where to paste it
Terminal
claude- Open a terminal in your repo and start Claude Code.
- Paste the sentence above.
- Approve the ShipGuard sign-in once when your browser opens.
What your agent runs
Step 1 · Install
npm i -g @agenticcli/shipguardInstalls the shipguard command. Runs on your machine.
Step 2 · Sign in (one approval)
shipguard loginPrints a link and a code and opens your browser. Ask the person at the keyboard to approve it once. If the approval is not given in time, run shipguard login again.
Step 3 · First scan
shipguard scanRuns locally. The report is saved on your machine in .shipguard/reports/ (.shipguard/reports/latest.md and .shipguard/reports/latest.json).
Step 4 · Add the policy file
shipguard initCreates shipguard.policy.yml and the reports folder in this repo.
Step 5 · Hook: git
shipguard hookInstalls pre-push and pre-merge-commit hooks. They run shipguard scan --json --strict before every push and merge.
Step 6 · Hook: Claude Code
shipguard hook --target claudeAdds a Claude Code hook in .claude/settings.json that runs the same check when the agent pushes or merges. Skip it if you do not use Claude Code.
Claude Code gets both hooks: the git hooks, and shipguard hook --target claude, a hook that runs outside the model so it holds even if the agent would skip it.
Then it adds this to your repo
Last step · add this to CLAUDE.md in your repo
## ShipGuard - ShipGuard is the release gate for this repo. It runs locally; code never leaves this machine. - Reports are saved in .shipguard/reports/ (.shipguard/reports/latest.md, .shipguard/reports/latest.json). - Before every push or merge, run: shipguard scan --json --strict - Exit 0 means the scan completed: read "recommendation" in the JSON. Exit 1 means blocked: fix each finding with blocking:true, then scan again. - The hooks from "shipguard hook" run this automatically. Keep them on; do not skip them with --no-verify.
Reports are saved on your machine in .shipguard/reports/ inside the repo. Your code and your reports stay on your machine.
More
- The full script for agents
- llms.txt, the same script as plain text
- ShipGuard docs
- Set up ShipGuard in Codex
- Set up ShipGuard in Cursor