Skip to main content
Cross-AI review lets you send your phase plans to multiple AI providers simultaneously and collect structured feedback before any code is written. Each reviewer produces an independent assessment of the plan’s feasibility, risks, and gaps, and GSD synthesizes the results into a single REVIEWS.md artifact that the planner can consume directly to drive a more informed replan.

​
Running /gsd-review

Run /gsd-review --phase N to dispatch your phase plans to one or more AI reviewers. GSD reads the phase’s PLAN.md files, assembles a review prompt that includes the roadmap, requirements, and context, and sends it to each selected reviewer in parallel.
Produces: {phase}-REVIEWS.md — a structured document containing each reviewer’s feedback, severity classifications, and specific concerns about the plan

​
Default reviewer configuration

Rather than specifying reviewer flags on every run, set review.default_reviewers in config.json to scope the no-flag /gsd-review call to a subset of reviewers you always want:
With this config set, running /gsd-review --phase 2 with no flags will use Gemini and Codex. Explicit reviewer flags override this setting for that run. --all always runs the full detected set regardless of config.

​
How REVIEWS.md feeds back into planning

After /gsd-review completes, pass --reviews to /gsd-plan-phase to replan using the cross-AI feedback as additional context. The planner reads REVIEWS.md, incorporates HIGH and MEDIUM concerns into revised task sequencing and risk mitigation, and produces an updated set of PLAN.md files.
--reviews skips the research step by default — it assumes your RESEARCH.md is still valid and focuses the planner’s attention on addressing the specific concerns raised in REVIEWS.md. Combine --reviews --research to force a full research refresh before replanning.

​
Automated convergence loop

Run /gsd-plan-review-convergence N to automate the plan → review → replan cycle until no HIGH concerns remain. The command spawns a planning agent and one or more review agents, counts unresolved HIGH concerns in each cycle’s CYCLE_SUMMARY, and replans automatically until the plan converges or the cycle cap is reached.
1

Plan

Spawns a planning agent to produce PLAN.md for the phase.
2

Review

Dispatches the plan to selected AI reviewers in parallel.
3

Count HIGH concerns

Parses the CYCLE_SUMMARY from REVIEWS.md to count unresolved HIGH-severity concerns.
4

Converge or replan

If HIGH count is zero, the loop exits successfully. If HIGH count is non-zero and cycles remain, replans with --reviews feedback and repeats from Step 2.
5

Escalate on stall

If the HIGH count stops decreasing across cycles, the command warns about a stall and offers the choice to proceed manually or extend the cycle cap.
/gsd-plan-review-convergence is disabled by default. Enable it by setting workflow.plan_review_convergence: true in config.json before running the command.

​
Configuring per-reviewer model selection

You can specify which model each reviewer CLI should use by setting review.models.<cli> in config.json. When a key is absent, GSD uses each CLI’s configured default.
Set these values interactively via /gsd-config --integrations.

​
Prerequisites

Before using cross-AI review, verify that each reviewer you plan to use is installed, authenticated, and reachable from your terminal.
Cloud CLIs (Gemini, Codex, OpenCode, Qwen, Cursor): Run the CLI with --version or a simple query to confirm it is installed and authenticated with a valid API key.Antigravity (agy): Free with Google credentials. Install the CLI and authenticate with your Google account before running.
Local model servers (Ollama, LM Studio, llama.cpp) are supported as reviewers in /gsd-plan-review-convergence but not in /gsd-review. Use /gsd-plan-review-convergence with the --ollama, --lm-studio, or --llama-cpp flags to run the full convergence loop against a local model.