andyzengmath/soliton

Risk-adaptive multi-agent PR review for Claude Code & Cursor — 7 specialized agents catch bugs, security flaws, and AI hallucinations in parallel

1Stars on the repository
22Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

comment-accuracy

01

andyzengmath/soliton

Agent

Detects stale comments, docstring-signature mismatches, and contradicted NOTE/TODO/FIXME markers.

1 2mo ago A 26 tokens original MIT

consistency

02

andyzengmath/soliton

Agent

Checks changed code against project conventions and coding style.

1 2mo ago A 12 tokens original MIT

correctness

03

andyzengmath/soliton

Agent

Detects logic errors, off-by-one bugs, null handling issues, and race conditions.

1 2mo ago A 20 tokens original MIT

hallucination

05

andyzengmath/soliton

Agent

Detects AI-generated code issues — non-existent APIs, wrong signatures, deprecated dependencies.

1 2mo ago A 20 tokens original MIT

realist-check

07

andyzengmath/soliton

Agent

Confirms or downgrades CRITICAL findings post-synthesis using deployment context; requires a cited mitigation for any downgrade.

1 2mo ago A 27 tokens original MIT

risk-scorer

08

andyzengmath/soliton

Agent

Fast risk assessment of PR changes. Computes a 0-100 risk score from 6 weighted factors and recommends which review agents to dispatch.

1 2mo ago A 33 tokens original MIT

security

09

andyzengmath/soliton

Agent

Detects security vulnerabilities following OWASP Top 10 with data flow analysis.

1 2mo ago A 16 tokens original MIT

silent-failure

10

andyzengmath/soliton

Agent

Detects silent error-handling failures — empty catches, swallowed Promise rejections, optional-chaining-masked nullability, assertion-free tests.

1 2mo ago A 31 tokens original MIT

spec-alignment

11

andyzengmath/soliton

Agent

Verifies acceptance criteria from REVIEW.md / .claude/specs / PR description and runs mechanical wiring-verification greps (Stage 0, pre-swarm).

1 2mo ago B 37 tokens original MIT

synthesizer

12

andyzengmath/soliton

Agent

Merges, deduplicates, filters, and synthesizes findings from all review agents into a coherent review.

1 2mo ago A 26 tokens original MIT