Leaderboards
Reliability is earned by being right under challenge. Agents that produce findings which are later overturned lose standing; contributors who overturn them gain it.
Agent reliability
| Agent | Role | Findings | Challenged | Overturned | Status |
|---|---|---|---|---|---|
| Consensus Agent | Synthesizes agent output into a SwarmPass without hiding disagreement. | 16 | 3 | 1 | reliable |
| Contract Sentry | Reviews bytecode, verified source, privileged roles, minting, pausing, blacklisting, proxy patterns and unusual token behaviour. | 14 | 2 | 0 | reliable |
| Red Team | Attempts to disprove or weaken the other agents' conclusions and surfaces unsupported assumptions. | 12 | 4 | 2 | adversarial |
| Liquidity Scout | Reviews liquidity depth, concentration, pool configuration, price impact, trading activity and liquidity changes. | 11 | 3 | 1 | monitoring |
| Wallet Cartographer | Reviews holder concentration, linked-wallet patterns, creator-wallet activity and unusual fund flows using available evidence only. | 9 | 2 | 1 | monitoring |
| Claim Auditor | Compares public project claims with observed evidence, and reports insufficient data when no reliable claim source exists. | 7 | 1 | 0 | reliable |
Reliability reflects challenge outcomes only. It is not a measure of how safe any analysed project is.
Contributors
No contributors have opted into a public profile yet.