Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.
Skill Claude CodeCodex
Authors and audits Claude Code subagents, covering tool allowlist or denylist, model and effort, permissionMode, persistent memory, skills: preload, isolation worktrees, and the five-section system-prompt body. Use when a subagent is being designed or fixed, or when recurring work should move into a fresh isolated…
Skill Claude CodeCodex
Authors and audits CLAUDE.md, CLAUDE.local.md, and .claude/rules/.md, covering the four scopes (managed, user-global, project-team, project-personal), paths: for path-scoped rules, @path imports, splitting an oversized file, and debugging instructions the model ignores. Use when standing instructions are being written…
Skill Claude CodeCodex
Authors and audits Claude Code slash commands, covering argument design (full-argument, positional, and named forms), shell injection for live context, phase-structured bodies, approval gates before side effects, and the flat-file versus skill-directory choice. Use when a /name command is being built or fixed.…
Skill Claude CodeCodex
Executor for plans approved by /ac:plan. Runs entirely on the main thread (Opus 5) with an auto-continue policy of wave-by-wave looping until the plan is complete, no schedule/wakeup polling. Spawns tier-routed worker subagents (ac:plan-worker-quick → haiku, ac:plan-worker-junior → sonnet, ac:plan-worker-senior →…
Skill Claude CodeCodex
Git expert - atomic commits with style detection, rebase/squash, and history archaeology (blame, bisect, pickaxe). Use for git operations.
Skill Claude CodeCodex
Interactive planner for Claude Code main thread (Opus 5). Spawns parallel research via ac:explore, ac:librarian, optionally ac:oracle. Reads referenced files itself. Grills the user via AskUserQuestion with recommended-first walk-down branching. Audits the plan for reuse, quality, and efficiency before writing. Writes…
Skill Claude CodeCodex
Writes high-signal prompts for Claude Opus 5 (system prompts, subagent briefings, skill bodies, command bodies, agent bodies, CLAUDE.md files, .claude/rules/.md) and audits existing ones. Use whenever instructions are being authored or edited for any Claude to execute, even when the user does not say the word…
Skill Claude CodeCodex
Authors and audits Claude Code skills, covering SKILL.md frontmatter, directory layout, scope (project, user, plugin, managed), invocation control, and bundled references/ or scripts/. Use when a skill is being written or edited, when a recurring playbook is being captured, when allowed-tools or paths: need choosing…