~ / leaderboard / subagent / adversarial-verifier
Subagent · #498
adversarial-verifier
Adversarially verify a single claim or finding — actively try to REFUTE it, default to "refuted" when uncertain. Use to check bug reports, audit findings, or research claims before trusting them. Read
5rigs use it
0%of all rigs
9.0kavg rig context tax
Get it
$ npx degit pjt222/agent-almanac/agents .claude/agents From the most-starred rig that ships it: pjt222/agent-almanac. Same-named subagents in different rigs may differ — review before use.
Often used together with
designer · 2architect · 2first-principles · 2media · 1research · 1council · 1researcher · 1security · 1security · 1plan · 1
Rigs using adversarial-verifier (5)
pjt222/agent-almanac
Agent Almanac — a curated reference of executable skills, specialist agents, and teams for AI-assisted development, with interactive visualization
Orchestrator 24.1k tok · · Q10
Sanexxxx777/curated-claude-code
A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
Skill Collector 980 tok · · Q0
korthout/mac
dotfiles and package management for my mac
Fort Knox 2.3k tok · · Q18
devergehq/locus
Claude Code plugin that makes an agent plan before it codes — seven-phase decomposition with verifiable criteria, injected per-turn and enforced by hooks rather than requested in prose.
Orchestrator 2.9k tok · · Q0
rustcircle/c101
Multi-agent all gathered on a table to discuss lancelot with agentic workflows
Orchestrator 14.9k tok · · Q18