What can I use for free?

Free includes 5 Claim Checks, 5 Reviews, 5 Test Evidence runs, and 5 Blast Radius runs per month, plus unlimited Scan, Agent Harness, and Agent Skills. An account is required.

Pro makes Claim Check, Review, Test Evidence, and Blast Radius unlimited and includes the full IDE workflow, advanced configuration, and richer local history. It costs $19 per month.

Which command verifies that an agent completed its task?

Use shipmoor claim-check. It freezes the task into atomic obligations, binds each obligation to evidence, and returns READY only when the required claims are decided and satisfied.

When do I need to log in?

All product work requires an authorized account. On the first protected command, the CLI starts device authorization and resumes the command after approval. Non-interactive CI uses a Shipmoor token.

What counts against a Free command allowance?

Each top-level Claim Check, Review, Test Evidence, or Blast Radius execution counts once after admission. User and agent invocations count the same, and a rerun consumes another unit. Review or Test Evidence composed internally by one Claim Check does not consume a separate allowance.

The local Shipmoor command line

One CLI for the complete agent verification loop.

Q: Does Shipmoor upload my source code?

The CLI runs locally or in your CI runner. Your source code and diffs are not uploaded. Shipmoor only contacts the service for authentication, entitlements, command allowances, and features you explicitly enable.

Q: Can I use the CLI in continuous integration?

Yes. Current self-managed CI supports authenticated Scan with stable exit codes and SARIF output. Supply a Scan-scoped machine token through SHIPMOOR_TOKEN. Claim Check, Review, Test Evidence, and Blast Radius remain local commands; managed CI is coming with Team.

Check whether an agent completed the task it was given. Verify that tests really ran and were not weakened. Scan for structural defects. Run advisory review with your own agent. Keep deterministic Scan active inside the agent loop and in continuous integration.

Shipmoor CLI is the local interface for the complete agent verification loop. Free includes separate monthly allowances for Claim Check, Review, Test Evidence, and Blast Radius, plus unlimited Scan, Agent Skills, and Agent Harness. Pro is $19 per month and unlimited.

Claim Check is the main verification command. It decides whether an agent generated change earned its completion claim. The other commands provide the evidence and workflow controls that make that verdict trustworthy.

Start free Start free Read the docs Read the docs

Runs locally
Free account · Local execution · No source upload
No Shipmoor hosted model

Claim Check
Test Evidence
Deterministic Scan
Advisory Code Review
Agent Skills
Agent Harness
Blast Radius

$ shipmoor claim-check --intent-prompt "add retry handling to failed webhooks" --agent claude . Claim Check is BLOCKED. One obligation has diverged.  The build passed. The tests passed. The scan passed.  AC 02 is blocked because retry stops after the first failure.  The evidence is located in src/webhooks/retry.ts at line 47.  The fix packet asks for a check that proves retries continue to the configured limit. $ shipmoor claim-check --agent claude . Claim Check is READY. Both obligations are verified.The attestation was written to .shipmoor/claim-check.vsa.json.

Claim Check is the main verification command. It returns a verdict and gives the agent a concrete path to resolve every blocker.

Start with unlimited Scan on Free

Authorize the CLI with your Free account, then run it in the repository where your coding agent made the change. Scan checks changed files for high-confidence structural defects and is unlimited on Free and Pro.

shipmoor scan --changed

Use it after Cursor, Claude Code, Codex, Copilot, Aider, or any coding agent that changes files in your repository.

Let the coding agent finish its change.
Run shipmoor scan on the changed files.
Resolve the reported structural defects.
Run the scan again before you push.

Seven command groups cover the full loop

Free includes unlimited Scan, Agent Harness, and Agent Skills, plus 5 monthly runs each for Claim Check, Review, Test Evidence, and Blast Radius. Pro makes every command unlimited.

Verify the change against the original task
shipmoor claim-check --intent-prompt "add retry handling" --agent claude .
Verify that tests ran and were not reduced or weakened
shipmoor test-evidence .
Scan changed files for deterministic structural defects
shipmoor scan --changed
Run advisory review with your own coding agent
shipmoor review --agent claude --from main --to HEAD
Map the change's dependency and impact radius
shipmoor blast .
Install Shipmoor skills into your coding agent
shipmoor skills install claude
Route verification results back into the agent loop
shipmoor harness mode feedback

Claim Check owns the final completion verdict. The other commands produce evidence, provide advisory findings, or keep verification active while the agent works.

What each part of the CLI contributes

Shipmoor does not treat every quality signal as the same kind of proof. Each command has a clear responsibility, and Claim Check combines the evidence without allowing an advisory model to approve the change.

One command with four levels of access

A new personal account receives one 30-day period of full Pro at account creation, with no card or invitation required. After that, use Free or upgrade to unlimited Pro. Team and Enterprise are coming soon; contact us for those plans.

$0
Free

Useful recurring local verification with separate monthly allowances.
- Claim Check: 5/month
- Review: 5/month
- Test Evidence: 5/month
- Blast Radius: 5/month
- Unlimited Scan, Agent Harness, and Agent Skills
$19 per month
Pro

Unlimited individual verification and the full advanced workflow.
- Unlimited Claim Check, Review, Test Evidence, and Blast Radius
- Unlimited Scan, Agent Harness, and Agent Skills
- Full IDE workflow and advanced configuration
- Richer local history
Coming soon
Team

Shared enforcement for engineering teams.
- Everything in Pro
- Managed continuous integration gates
- Shared policy and baselines
- Pull request comments
Coming soon
Enterprise

Governance and deployment controls for larger organizations.
- Everything in Team
- Organization administration
- Single sign on and audit logs
- Private or self hosted runners

One account across the product

All product commands require an authorized account or CI token. A new personal account receives its one 30-day period of full Pro when the account is created, with no card or invitation required; it then falls back to Free unless you subscribe.

shipmoor login
shipmoor whoami
shipmoor capabilities --json

There is one binary and one account across the CLI, editor, Skills, and Agent Harness.

Local by design

The CLI runs in your development environment or CI runner. Your source code and diffs are not uploaded. Shipmoor only contacts the service for authentication, entitlements, command allowances, and features you explicitly enable. Features that need an agent use the coding agent and provider relationship you already control.

Use the free Scan in continuous integration

The same deterministic Scan that runs before a push can gate a pull request and publish SARIF findings. Current self-managed CI is Scan-only and requires a Scan-scoped machine token.

name: Shipmoor scan

on:
  pull_request:

jobs:
  shipmoor:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Install Shipmoor
        run: curl -fsSL https://dl.shipmoor.dev/install.sh | bash

      - name: Run the deterministic Scan
        env:
          SHIPMOOR_TOKEN: ${{ secrets.SHIPMOOR_TOKEN }}
        run: shipmoor scan --diff origin/main...HEAD --fail-on high --sarif --output shipmoor.sarif

      - name: Upload SARIF
        uses: github/codeql-action/upload-sarif@v3
        with:
          sarif_file: shipmoor.sarif
        if: always()

Current self-managed CI is Scan-only and uses a Scan-scoped machine token through SHIPMOOR_TOKEN. Run Claim Check, Review, Test Evidence, and Blast Radius locally; managed CI for broader verification is coming with Team.

From agent output to an earned verdict

Shipmoor belongs inside the coding loop, before a completion claim reaches human review. The CLI collects evidence early and gives the agent a direct path to resolve every blocker.

The agent changes code then
Shipmoor collects evidence then
Claim Check returns a verdict then
A reviewer evaluates the change then
The change can merge

Human review still matters. Shipmoor makes sure that review starts with an explicit task, credible evidence, and an honest completion state.

Install the CLI and start locally

A new personal account receives one 30-day period of full Pro at account creation with no card. Then keep 5 monthly runs each of Claim Check, Review, Test Evidence, and Blast Radius plus unlimited Scan, Agent Harness, and Agent Skills, or choose unlimited Pro for $19 per month.

Install Shipmoor

Free account. Local execution. No source upload.

Start free

curl -fsSL https://dl.shipmoor.dev/install.sh | bash

Read the documentation

Questions about Shipmoor CLI Frequently asked questions

Clear answers about Free allowances, unlimited Pro, local execution, and the main verification commands.

One CLI for the complete agent verification loop.

Claim Check

Test Evidence

Scan

Code Review

Agent Skills

Agent Harness

Free

Pro

Team

Enterprise

Local by design

Install the CLI and start locally

Install Shipmoor

Questions about Shipmoor CLI Frequently asked questions

What can I use for free?

What does Pro add?

Which command verifies that an agent completed its task?

When do I need to log in?

What counts against a Free command allowance?

Does Shipmoor upload my source code?

Can I use the CLI in continuous integration?

Continue with