Agent Claude Code
Adversarial code reviewer that tries to break code. Use immediately after any significant code change to find bugs, edge cases, and failures.
not rated 19 4mo ago A 34 tokens
original MIT
19Stars on the repository
15Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
architect
02Agent Claude Code
System architecture specialist for design decisions, ADRs, and technical trade-offs. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions. Never writes implementation code.
not rated 19 4mo ago A 42 tokens
original MIT
Agent Claude Code
Multi-pass self-review that forces write-critique-rewrite-verify cycle. Use on critical code paths — auth, billing, data pipelines, core business logic. Catches issues single-pass review misses. Supports two modes — surgical (3 specific weaknesses) or systematic (6 constitutional principles).
not rated 19 4mo ago A 62 tokens
original MIT
Agent Claude Code
Visual design reviewer that critiques UI output. Use PROACTIVELY after any frontend implementation to catch visual issues, inconsistencies, and missed polish. Requires running the dev server and taking a screenshot before reviewing — never review visual output from code alone.
not rated 19 4mo ago A 53 tokens
original MIT
Agent Claude Code
Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability.
not rated 19 4mo ago A 40 tokens
original MIT
Agent Claude Code
Generates property-based tests that find edge cases humans miss. Use for pure functions, parsers, serializers, data transformations, and any code where input space is large.
not rated 19 4mo ago A 39 tokens
original MIT
Agent Claude Code
Verifies that new code is actually wired into the running system — not orphaned. Use PROACTIVELY after any implementation to catch dead code, unregistered routes, unrendered components, and disconnected modules. The.
not rated 19 4mo ago A 48 tokens
original MIT
Agent Claude Code
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage, correctness). Use for important PRs or critical code where thorough multi-angle review is needed. Each perspective has blinders — forces deeper analysis per domain.
not rated 19 4mo ago A 56 tokens
original MIT
red-team
09Agent Claude Code
Security red team specialist. Attacks the developer's stated security assumptions. Use proactively when code touches auth, billing, API, or infrastructure.
not rated 19 4mo ago A 31 tokens
original MIT
researcher
10Agent Claude Code
Multi-depth research agent with configurable intensity. Use for any research task — from quick lookups to nuclear-level exhaustive investigations. Specify depth in the prompt: surface, basic, deep, in-depth, ultra, nuclear, overkill.
not rated 19 4mo ago A 49 tokens
original MIT
Agent Claude Code
Mandatory pre-implementation interrogation. Use before any non-trivial coding task to surface assumptions, find existing solutions, and prevent over-engineering. Forces 6 critical questions before a single line of code.
not rated 19 4mo ago A 45 tokens
original MIT
Agent Claude Code
Pre-implementation requirements interviewer. Use BEFORE any non-trivial feature, refactor, or new project. Reads the codebase, asks 20-40 probing questions in structured rounds, and produces a bulletproof SPEC.md with testable acceptance criteria, exact files to modify, and a wiring checklist. Never writes…
not rated 19 4mo ago A 69 tokens
original MIT
Agent Claude Code
Detects fake, theatrical, and meaningless tests. Use PROACTIVELY after test suites are written to catch mock-everything tests, tautological assertions, happy-path-only coverage, and tests that pass but verify nothing. The anti-"test theater" agent.
not rated 19 4mo ago A 57 tokens
original MIT
Agent Claude Code
Explores multiple solution approaches before committing to one. Use proactively for algorithm selection, data structure choices, or any decision where 3+ fundamentally different approaches exist.
not rated 19 4mo ago A 37 tokens
original MIT
ui-architect
15Agent Claude Code
Frontend UI/UX design specialist. Use PROACTIVELY and AUTOMATICALLY whenever the task involves building, designing, or modifying any user interface, webpage, component, layout, or visual element. This includes React, Next.js, Vue, Svelte, HTML/CSS, Tailwind, or any frontend framework.
not rated 19 4mo ago A 68 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: