diff --git a/README.md b/README.md index 0b082f4ee..29d49a6a5 100644 --- a/README.md +++ b/README.md @@ -177,6 +177,13 @@ Produces: Each phase breaks into 2-3 atomic tasks. Each task runs in a fresh subagent context — 200k tokens purely for implementation, zero degradation. +**For multi-plan phases:** +``` +/gsd:execute-phase 1 # Run all plans in parallel, "walk away" execution +``` + +Use `/gsd:execute-plan` for interactive single-plan execution with checkpoints. Use `/gsd:execute-phase` when you have multiple plans and want parallel "walk away" automation. + ### 4. Ship and iterate ``` @@ -316,7 +323,8 @@ You're never locked in. The system adapts. | `/gsd:create-roadmap` | Create roadmap and state tracking | | `/gsd:map-codebase` | Map existing codebase for brownfield projects | | `/gsd:plan-phase [N]` | Generate task plans for phase | -| `/gsd:execute-plan` | Run plan via subagent | +| `/gsd:execute-plan` | Run single plan via subagent | +| `/gsd:execute-phase ` | Execute all plans in phase N with parallel agents | | `/gsd:progress` | Where am I? What's next? | | `/gsd:verify-work [N]` | User acceptance test of phase or plan ¹ | | `/gsd:plan-fix [plan]` | Plan fixes for UAT issues from verify-work | diff --git a/commands/gsd/help.md b/commands/gsd/help.md index 2b6fafefe..8352e68ef 100644 --- a/commands/gsd/help.md +++ b/commands/gsd/help.md @@ -107,15 +107,29 @@ Result: Creates `.planning/phases/01-foundation/01-01-PLAN.md` ### Execution **`/gsd:execute-plan `** -Execute a PLAN.md file directly. +Execute a single PLAN.md file. - Runs plan tasks sequentially - Creates SUMMARY.md after completion - Updates STATE.md with accumulated context -- Fast execution without loading full skill context +- Use for interactive execution with checkpoints Usage: `/gsd:execute-plan .planning/phases/01-foundation/01-01-PLAN.md` +**`/gsd:execute-phase `** +Execute all unexecuted plans in a phase with parallel background agents. + +- Analyzes plan dependencies and spawns independent plans concurrently +- Use when phase has 2+ plans and you want "walk away" execution +- Respects max_concurrent_agents from config.json + +Usage: `/gsd:execute-phase 5` + +Options (via `.planning/config.json` parallelization section): +- `max_concurrent_agents`: Limit parallel agents (default: 3) +- `skip_checkpoints`: Skip human checkpoints in background (default: true) +- `min_plans_for_parallel`: Minimum plans to trigger parallelization (default: 2) + ### Roadmap Management **`/gsd:add-phase `**