/gaia-review-all

user-facing
Category:
Reviews
Lifecycle phase:
4 -- Implementation
Arguments:
[story-key] [--force]

What it does

/gaia-review-all runs all six review workflows sequentially for a story: Code Review, QA Tests, Security Review, Test Automation, Test Review, and Performance Review. Each review updates the story's Review Gate table. Reviews that already passed are skipped unless --force is specified.

When to use it

  • A story is in review status and you want to run all six reviews in one pass rather than invoking each individually.

Prerequisites

  • Story must be in review status. Run /gaia-dev-story first to implement and transition the story.

Orchestration mode

When /gaia-review-all starts in subagent mode (Mode A -- the default), the framework emits a one-shot warning to your conversation. The warning text:


────────────────────────────────────────────────────────────────────────────
GAIA orchestration: running in subagent mode (Mode A)

The skill you're invoking belongs to a class (heavy-procedural or
conversational) whose output benefits from cross-step context. Mode A
dispatches each sub-agent in its own forked context, so context may
be lossy between steps — sub-agents return summaries, not full reasoning.

For the full-fidelity experience, enable Mode B (Agent Teams):
  1. Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in your environment.
  2. Add orchestration.mode: team to .gaia/config/project-config.yaml.

Mode B uses persistent teammates that preserve in-conversation state
across dispatches.

This warning is shown once per session.
────────────────────────────────────────────────────────────────────────────

Why Mode B is better for this command

The /gaia-review-all skill declares orchestration_class: heavy-procedural in its SKILL.md frontmatter. Heavy-procedural skills produce output that benefits from cross-step context -- under Mode A every sub-agent dispatch runs in its own forked context and can only return a summary back to the orchestrator, losing the full reasoning trace of every prior step. Mode B uses persistent teammates that retain in-conversation state across dispatches, so each agent's contribution can build on what was said before instead of receiving only a summary.

How to enable Mode B

Both steps are required. If either is missing, the framework falls back silently to Mode A and the warning fires again on the next session.

Step 1 -- set the environment variable:

export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

Add this to your shell rc file to persist across sessions, or set it in Claude Code's settings.json.

Step 2 -- add the YAML block to .gaia/config/project-config.yaml:

orchestration:
  mode: team

One-shot semantics

The warning is emitted once per Claude Code session. A marker file at _memory/checkpoints/orchestration-warning-shown.<session-id> suppresses the warning for the rest of the session. Starting a new session re-emits the warning once.

How to invoke

/gaia-review-all E3-S7

What it does step by step

  1. Validate input Confirms the story exists and is in review status.
  2. Check for prior results Determines which reviews already passed. Skips them unless --force is set.
  3. Run reviews sequentially Executes each review in canonical order, updating the Review Gate after each. Never short-circuits on failure -- all six reviews run to surface all issues.
  4. Generate summary Writes a summary with per-review verdicts and suggests next steps.

Inputs

The command reads the story file, its associated source files (from the Dev Agent Record file list), and project configuration automatically.

Outputs

Each review produces a report in .gaia/artifacts/implementation-artifacts/. The story file's Review Gate table is updated with PASSED or FAILED for each review.

Example session

> /gaia-review-all E3-S7

Running 6 reviews for E3-S7...

1. Code Review       PASSED
2. QA Tests          PASSED
3. Security Review   REQUEST_CHANGES -- 1 finding (hardcoded secret)
4. Test Automation   PASSED
5. Test Review       PASSED
6. Performance Review PASSED

Review Gate: 5/6 passed, 1 failed.
Fix the security finding and re-run: /gaia-review-all E3-S7

What to run next

After all reviews pass, run /gaia-check-review-gate to verify the composite gate status and transition the story to done.

Troubleshooting

"Story must be in review status"

The story has not been implemented yet. Run /gaia-dev-story first.

A reviewer crashed

The crashed reviewer is recorded as FAILED and the remaining reviews continue. Fix the underlying issue and re-run with --force.

I keep seeing the GAIA orchestration warning every time I start this command

The warning is shown once per session, so if it fires again that's a new session -- not a per-skill repeat. If you want to silence it entirely, enable Mode B (full-fidelity orchestration via Agent Teams). Both of these conditions must be true:

  • echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS returns 1 (not empty)
  • .gaia/config/project-config.yaml contains: 
    orchestration:
  mode: team

If either is missing the framework silently uses Mode A and re-emits the warning each session.