ShipSafe: How a LinkedIn Post Sent Me Back Into My Old Field for 10 Hours

Description and use

ShipSafe is an automated agent that pulls PR diffs, runs tests in an isolated sandbox, aggregates results, and requires explicit human approval before posting a review comment.

Problem

Pull request reviews are tedious and error‑prone; reviewers often skim diffs and assume tests pass, allowing bugs to slip through.

Outcome

ShipSafe completed a PR review in under 10 hours, ran tests in a sandbox, and required explicit human approval before posting, catching a real bug that Qodo also identified.

Workflow

• Register for Agent Harness Hackathon
• Create empty repo and ship-safe.json agent definition
• Use TrueForge harness to call GitHub MCP for PR data
• Spin up Daytona sandbox to run tests (npm test or test.py)
• If multiple files changed, spawn subagents per file
• Aggregate subagent verdicts into a review summary
• Show review to user and ask for approval to post comment
• Persist session state across page refreshes
• Merge PR after user approves review

Evidence

ShipSafe talks to GitHub through an MCP server, not a hand‑rolled API client.

Source

ShipSafe runs tests in a Daytona sandbox, never on my host machine.

Source