architect
01Agent Claude Code
Use only for ambiguous high-impact cross-module design, major migrations, and difficult root-cause analysis after ordinary investigation is insufficient.
not rated 5 1mo ago A 27 tokens
original MIT
explorer
02Agent Claude Code
Use proactively for read-only file and symbol discovery, execution tracing, log inspection, and evidence gathering before a change or review. Use @explorer when a cost-controlled exploration pass is required.
not rated 5 1mo ago A 41 tokens
original MIT
implementer
03Agent Claude Code
Use for one well-scoped feature, bug fix, test update, or routine refactor after the affected code path and acceptance criteria are understood.
not rated 5 1mo ago A 32 tokens
original MIT
reviewer
04Agent Claude Code
Use for a read-only review of correctness, security, regressions, data consistency, and missing test coverage after a change or proposed approach.
not rated 5 1mo ago A 31 tokens
original MIT
Skill Codex
Initialize, inspect, safely reconcile upgrades for, and operate Repo Continuity. Use when an agent needs to install the repository-owned knowledge layer; produce a read-only three-way upgrade report or apply only conflict-free upstream changes without overwriting project customization; route work into Direct, Tracked…
not rated 5
changed 1mo ago A 171 tokens
original MIT
Skill Claude CodeCodex
Describe what this procedure does and the concrete repository situations that should trigger it.
not rated 5 1mo ago A 20 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: