/gaia-edit-test-plan

What it does

/gaia-edit-test-plan adds new test cases to an existing test plan while preserving all existing content. Edits are strictly additive -- existing test cases, strategy, environments, and entry/exit criteria are never removed or modified. Test case IDs auto-increment from the highest existing ID.

When to use it

• New requirements were added (via PRD edit or architecture change) and the test plan needs matching test cases.
• A gap analysis identified missing test coverage.

Prerequisites

• Test plan must exist at .gaia/artifacts/test-artifacts/test-plan.md.

Orchestration mode

When /gaia-edit-test-plan 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-edit-test-plan 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-edit-test-plan

What it does step by step

1. Load test plan Reads the existing test plan. Displays: section count, test case count, coverage areas, and highest test case ID.
2. Capture change scope Asks what new test cases are needed. If triggered by an upstream command (like /gaia-add-feature), inherits the context automatically.
3. Define new test cases Creates new test cases in the same format as existing ones, with auto-incremented IDs and proper categorization.
4. Update coverage summary Updates the coverage summary to reflect the new test cases.
5. Save Appends the new test cases, adds a version note, and writes the updated test plan.

Inputs

Outputs

Example session

> /gaia-edit-test-plan

Current test plan: 42 test cases (TC-001 to TC-042).

What new test cases are needed?
> Add test cases for the new rate limiting feature (NFR-009)

New test cases:
  TC-043: Rate limit returns 429 after 100 requests/minute
  TC-044: Rate limit resets after cooldown period
  TC-045: Rate limit applies per-user, not globally

Coverage updated. Version note added.
Written to: .gaia/artifacts/test-artifacts/test-plan.md

What to run next

• /gaia-readiness-check -- re-validate readiness with the updated test plan.

Troubleshooting

"test-plan.md not found"

Run /gaia-test-strategy to create the initial test plan.

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.

Related commands