From 82c522b8c3fbc6f53cb21ac515b977239c207f8d Mon Sep 17 00:00:00 2001 From: Lex Christopherson Date: Thu, 15 Jan 2026 09:40:53 -0600 Subject: [PATCH] fix: update remaining general-purpose refs to gsd-executor - execute-phase.md: wave execution example now uses gsd-executor - execute-plan.md workflow: subagent spawning uses gsd-executor - continuation-prompt.md: continuation spawning uses gsd-executor - Remove obsolete subagent-task-prompt.md reference Co-Authored-By: Claude --- commands/gsd/execute-phase.md | 7 +++---- get-shit-done/templates/continuation-prompt.md | 2 +- get-shit-done/workflows/execute-plan.md | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/commands/gsd/execute-phase.md b/commands/gsd/execute-phase.md index 14be4e377..145849b24 100644 --- a/commands/gsd/execute-phase.md +++ b/commands/gsd/execute-phase.md @@ -25,7 +25,6 @@ Context budget: ~15% orchestrator, 100% fresh per subagent. @~/.claude/get-shit-done/references/principles.md @~/.claude/get-shit-done/workflows/execute-phase.md -@~/.claude/get-shit-done/templates/subagent-task-prompt.md @~/.claude/get-shit-done/templates/subagent-verify-prompt.md @~/.claude/get-shit-done/workflows/verify-phase.md @@ -173,9 +172,9 @@ All {N} phases finished. Spawn all plans in a wave with a single message containing multiple Task calls: ``` -Task(prompt=filled_template_for_plan_01, subagent_type="general-purpose") -Task(prompt=filled_template_for_plan_02, subagent_type="general-purpose") -Task(prompt=filled_template_for_plan_03, subagent_type="general-purpose") +Task(prompt="Execute plan at {plan_01_path}\n\nPlan: @{plan_01_path}\nProject state: @.planning/STATE.md", subagent_type="gsd-executor") +Task(prompt="Execute plan at {plan_02_path}\n\nPlan: @{plan_02_path}\nProject state: @.planning/STATE.md", subagent_type="gsd-executor") +Task(prompt="Execute plan at {plan_03_path}\n\nPlan: @{plan_03_path}\nProject state: @.planning/STATE.md", subagent_type="gsd-executor") ``` All three run in parallel. Task tool blocks until all complete. diff --git a/get-shit-done/templates/continuation-prompt.md b/get-shit-done/templates/continuation-prompt.md index b7f4f9bf4..800afa1d1 100644 --- a/get-shit-done/templates/continuation-prompt.md +++ b/get-shit-done/templates/continuation-prompt.md @@ -228,7 +228,7 @@ Orchestrator fills placeholders from checkpoint return and user response: ```python Task( prompt=filled_continuation_template, - subagent_type="general-purpose" + subagent_type="gsd-executor" ) ``` diff --git a/get-shit-done/workflows/execute-plan.md b/get-shit-done/workflows/execute-plan.md index 171ca7477..24cbfde46 100644 --- a/get-shit-done/workflows/execute-plan.md +++ b/get-shit-done/workflows/execute-plan.md @@ -205,7 +205,7 @@ No segmentation benefit - execute entirely in main ``` 1. Run init_agent_tracking step first (see step below) -2. Use Task tool with subagent_type="general-purpose": +2. Use Task tool with subagent_type="gsd-executor": Prompt: "Execute plan at .planning/phases/{phase}-{plan}-PLAN.md @@ -357,7 +357,7 @@ For Pattern A (fully autonomous) and Pattern C (decision-dependent), skip this s B. If routing = Subagent: ``` - Spawn Task tool with subagent_type="general-purpose": + Spawn Task tool with subagent_type="gsd-executor": Prompt: "Execute tasks [task numbers/names] from plan at [plan path].