From 6fe78d4bde84155947384620be9013d2e7de3763 Mon Sep 17 00:00:00 2001 From: citizen204 Date: Tue, 9 Jun 2026 15:48:45 +0930 Subject: [PATCH] docs: clarify session terminology in SDD and writing-plans Fixes #1478 --- skills/subagent-driven-development/SKILL.md | 13 ++++++------- skills/writing-plans/SKILL.md | 10 +++++----- 2 files changed, 11 insertions(+), 12 deletions(-) diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.md index ea7ac8fd8b..d11ec7c546 100644 --- a/skills/subagent-driven-development/SKILL.md +++ b/skills/subagent-driven-development/SKILL.md @@ -19,23 +19,22 @@ Execute plan by dispatching fresh subagent per task, with two-stage review after digraph when_to_use { "Have implementation plan?" [shape=diamond]; "Tasks mostly independent?" [shape=diamond]; - "Stay in this session?" [shape=diamond]; + "Coordinate from this session?" [shape=diamond]; "subagent-driven-development" [shape=box]; "executing-plans" [shape=box]; "Manual execution or brainstorm first" [shape=box]; "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"]; "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"]; - "Tasks mostly independent?" -> "Stay in this session?" [label="yes"]; + "Tasks mostly independent?" -> "Coordinate from this session?" [label="yes"]; "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"]; - "Stay in this session?" -> "subagent-driven-development" [label="yes"]; - "Stay in this session?" -> "executing-plans" [label="no - parallel session"]; + "Coordinate from this session?" -> "subagent-driven-development" [label="yes"]; + "Coordinate from this session?" -> "executing-plans" [label="no - single-agent execution"]; } ``` -**vs. Executing Plans (parallel session):** -- Same session (no context switch) -- Fresh subagent per task (no context pollution) +**vs. Executing Plans (single-agent execution):** +- This session coordinates; fresh subagent per task (no context pollution) - Two-stage review after each task: spec compliance first, then code quality - Faster iteration (no human-in-loop between tasks) diff --git a/skills/writing-plans/SKILL.md b/skills/writing-plans/SKILL.md index 847412ece1..3d4bf5583e 100644 --- a/skills/writing-plans/SKILL.md +++ b/skills/writing-plans/SKILL.md @@ -137,16 +137,16 @@ After saving the plan, offer execution choice: **"Plan complete and saved to `docs/superpowers/plans/.md`. Two execution options:** -**1. Subagent-Driven (recommended)** - I dispatch a fresh subagent per task, review between tasks, fast iteration +**1. Subagent-Driven (recommended)** - I coordinate from this session, dispatch a fresh subagent per task, review between tasks, fast iteration -**2. Inline Execution** - Execute tasks in this session using executing-plans, batch execution with checkpoints +**2. Single-Agent Execution** - Execute tasks directly using executing-plans, batch execution with checkpoints **Which approach?"** **If Subagent-Driven chosen:** - **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development -- Fresh subagent per task + two-stage review +- Fresh subagent per task + two-stage review; this session acts as coordinator -**If Inline Execution chosen:** +**If Single-Agent Execution chosen:** - **REQUIRED SUB-SKILL:** Use superpowers:executing-plans -- Batch execution with checkpoints for review +- Batch execution with checkpoints for review; no subagent dispatch