~ / leaderboard / subagent / judge
Subagent · #377 
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce stru
5rigs use it
0%of all rigs
3.8kavg rig context tax
Get it
$ npx degit parcadei/Continuous-Claude-v3/.claude/agents .claude/agents From the most-starred rig that ships it: parcadei/Continuous-Claude-v3. Same-named subagents in different rigs may differ — review before use.
Often used together with
test-driven-development · 2researcher · 2commit · 2implement-task · 2recall · 2remember · 2receiving-code-review · 1requesting-code-review · 1systematic-debugging · 1investigator · 1
Rigs using judge (5)
parcadei/Continuous-Claude-v3
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Orchestrator 3.1k tok ·
NeoLabHQ/context-engineering-kit
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.
Orchestrator 8.3k tok ·
click6067-ship-it/ultrapowers
A Claude Code + Codex setup: two-model adversarial planning review (no-echo scoring), auditable council logs, and cross-session memory. Built on superpowers.
Orchestrator 3.3k tok ·
kentian742-creator/owners-office
One private investor's research, kept in public and put to the test: theses on seven US-listed companies, each with 20-30 tests that could prove it wrong; earnings forecasts timestamped before results and scored after; a public mistakes log
Orchestrator 3.1k tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·