The outcome

Add repeatable AI-assisted review without letting the reviewer silently fix, execute, or publish code.

OpenCode is a open-source AI coding agent for terminal, desktop, and editor workflows. Using plan, build, exploration, and custom agents across repositories while controlling models, commands, edits, external directories, web access, skills, and subagents. This guide narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Define the review scope, threat model, severity rubric, allowed evidence, safe commands, provider, maximum steps, and required output format.

  2. 02

    Create a project-scoped review agent whose edit, external-directory, network, skill, MCP, and subagent permissions are denied unless explicitly justified.

  3. 03

    Allow only read operations and specific diagnostic commands, keeping broad shell patterns, environment files, credentials, pushes, and package installation blocked.

  4. 04

    Test the agent on known defects, false positives, hostile comments, generated files, secrets, large diffs, and requests to bypass its permissions.

  5. 05

    Require exact file evidence and reproduction steps, verify consequential findings manually, and version the agent configuration with owner review.

Working standard

What good use looks like.

  • Deny edits in the reviewer.
  • Allowlist exact diagnostics.
  • Manually verify high-severity findings.

Provider terms, credential storage, agent definitions, permission syntax, and defaults can change across versions. Pin the version and current documentation, deny secrets and external directories by default, keep shell, edits, web access, skills, MCP tools, and subagents least-privileged, review saved approvals, avoid auto mode on untrusted repositories, bound iterations and cost, and independently verify every change.

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this collection.