What’s New

superpowers v5.0.6

v5.0.6
Added
  • Add explicit "No Placeholders" section in writing-plans defining plan failures as TBD, vague descriptions, undefined references, and references similar to Task N
  • Add named agent dispatch mapping documenting translation from Claude Code's named agent types to Codex spawn_agent with worker roles
  • Add environment detection and Codex App finishing sections for worktree-aware skills
  • Add Codex App compatibility design spec covering read-only environment detection, worktree-safe skill behavior, and sandbox fallback patterns
Changed
  • Replace subagent review loops in brainstorming with inline Spec Self-Review checklist covering placeholder scan, internal consistency, scope check, and ambiguity check
  • Replace Plan Review Loop in writing-plans with inline Self-Review checklist covering spec coverage, placeholder scan, and type consistency
  • Restructure brainstorm server session directory to separate content/ and state/ subdirectories, with both screen_dir and state_dir paths included in server-started JSON
Fixed
  • Fix brainstorm server owner-PID monitoring false shutdowns by treating EPERM as alive and validating owner PID at startup to disable monitoring if already dead
  • Correct writing-skills documentation to say SKILL.md frontmatter supports two required fields and link to agentskills.io specification
Removed
  • Remove Windows/MSYS2-specific carve-out from start-server.sh
Inline Self-Review Replaces Subagent Review Loops

The subagent review loop (dispatching a fresh agent to review plans/specs) doubled execution time (~25 min overhead) without measurably improving plan quality. Regression testing across 5 versions with 5 trials each showed identical quality scores regardless of whether the review loop ran.

  • brainstorming — replaced Spec Review Loop (subagent dispatch + 3-iteration cap) with inline Spec Self-Review checklist: placeholder scan, internal consistency, scope check, ambiguity check
  • writing-plans — replaced Plan Review Loop (subagent dispatch + 3-iteration cap) with inline Self-Review checklist: spec coverage, placeholder scan, type consistency
  • writing-plans — added explicit "No Placeholders" section defining plan failures (TBD, vague descriptions, undefined references, "similar to Task N")
  • Self-review catches 3-5 real bugs per run in ~30s instead of ~25 min, with comparable defect rates to the subagent approach
Brainstorm Server
  • Session directory restructured — the brainstorm server session directory now contains two peer subdirectories: content/ (HTML files served to the browser) and state/ (events, server-info, pid, log). Previously, server state and user interaction data were stored alongside served content, making them accessible over HTTP. The screen_dir and state_dir paths are both included in the server-started JSON. (Reported by 吉田仁)
Bug Fixes
  • Owner-PID lifecycle fixes — the brainstorm server's owner-PID monitoring had two bugs causing false shutdowns within 60 seconds: (1) EPERM from cross-user PIDs (Tailscale SSH, etc.) was treated as "process dead", and (2) on WSL the grandparent PID resolves to a short-lived subprocess that exits before the first lifecycle check. Fixed by treating EPERM as "alive" and validating the owner PID at startup — if it's already dead, monitoring is disabled and the server relies on the 30-minute idle timeout. This also removes the Windows/MSYS2-specific carve-out from start-server.sh since the server now handles it generically. (#879)
  • writing-skills — corrected false claim that SKILL.md frontmatter supports "only two fields"; now says "two required fields" and links to the agentskills.io specification for all supported fields (PR #882 by @arittr)
Codex App Compatibility
  • codex-tools — added named agent dispatch mapping documenting how to translate Claude Code's named agent types to Codex's spawn_agent with worker roles (PR #647 by @arittr)
  • codex-tools — added environment detection and Codex App finishing sections for worktree-aware skills (by @arittr)
  • Design spec — added Codex App compatibility design spec (PRI-823) covering read-only environment detection, worktree-safe skill behavior, and sandbox fallback patterns (by @arittr)
View original