Jesse Vincent b36cf86afd Require explicit model on subagent dispatch ...

In live eval runs, controllers given judgment-based model selection
stopped passing a model at all; the omitted parameter inherits the
session's top-tier model, silently making every subagent maximally
expensive (one run dispatched 26/26 reviewers on the session model).

2026-06-15 12:15:06 -07:00

..

brainstorming

Fix companion stop metadata and token permissions

2026-06-11 13:53:06 -07:00

dispatching-parallel-agents

Phase A: agent-neutral prose + CSO → SDO + spec

2026-05-13 17:46:28 -07:00

executing-plans

Phase D: cross-runtime tweaks (visual-companion, executing-plans, test)

2026-05-13 17:46:28 -07:00

finishing-a-development-branch

fix(finishing-a-development-branch): remove gh-specific PR creation instruction

2026-06-01 13:58:22 -07:00

receiving-code-review

Phase B: config-file refs + per-platform tool refs + spec

2026-05-13 17:46:28 -07:00

requesting-code-review

Convert curly to square brackets in code-reviewer.md placeholders

2026-05-23 16:14:24 -07:00

subagent-driven-development

Require explicit model on subagent dispatch

2026-06-15 12:15:06 -07:00

systematic-debugging

fix(systematic-debugging): defuse Claude Code ultrathink keyword scanner trigger (#1558)

2026-05-23 16:51:00 -07:00

test-driven-development

fix(tdd): link testing anti-patterns reference (#1532)

2026-05-12 17:22:42 -07:00

using-git-worktrees

fix: remove global worktree path fallback (#1476)

2026-05-12 10:24:45 -07:00

using-superpowers

feat: add Antigravity CLI (agy) support

2026-06-01 11:42:09 -07:00

verification-before-completion

Standardize skill frontmatter names to lowercase and kebab-case

2025-10-17 09:40:36 -07:00

writing-plans

Phase E: action-language tool vocabulary

2026-05-13 17:46:28 -07:00

writing-skills

fix(writing-skills): hang backfire mechanism on the separated prohibition-vs-recipe comparison (NEW-4); control comparison stated as trend

2026-06-11 12:11:37 -07:00