742 tagged code quality, measured the same way as everything else here.
Browse within: development-workflow 57architecture 55ai-pipeline 53autonomous-coding 53autofix 38ci-cd 37developer-productivity 37Multi-Agent 34ai-code-review 33AI Safety 30contracts 30agent-plugins 29antigravity 29bug-hunter 29
Agent
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…
Agent
Fresh-eyes, coverage-first quality judge for sweep passes on any deliverable (code, UI, copy, video frames, research, prompts). Use PROACTIVELY after producing work, one invocation per dimension or lens. Give it the rubric (or the craft file path), the evidence (file paths, screenshot paths, run output), and the lens…
Agent Claude Code
Help the user when they ask for things. Be helpful.
Agent
Layer 3 systematically scans ALL entry points from Layer 1 and applies issue detection rules. Unlike Layer 2 (which traces specific flows in depth), Layer 3 does a breadth-first scan to categorize issues across the entire codebase.
Agent
Layer 4 evaluates workflows from the user's perspective. While Layers 1-3 analyze code structure, Layer 4 asks: "Does this workflow help the user achieve their goal?".
Agent
Layer 5 verifies that features use real user data instead of mock/hardcoded values, and that model capabilities are fully wired into the features that need them. While Layers 1-4 audit navigation and UX, Layer 5 audits whether the data flowing through those workflows is genuine.
Agent
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
Agent
Status: binding (era-13.5 gate G7) Code: crates/argot-core/src/scoring/calibration.rs — runcalibrate (multi-seed median threshold).
Agent
If any of these files don't exist, proceed silently. Don't flag their absence upfront.
Agent
Companion to calibration-contract.md, which governs the base statistical scorer. The semantic layer (feature semantic, crate crates/argot-rules-semantic/) calibrates itself separately at fit time; this file records the invariants a contributor must not break.
cubetribe/ClaudeCode_GodMode-On
Agent
GitHub Project Management Specialist for issues, PRs, releases, repository sync, and CI/CD orchestration.
cubetribe/ClaudeCode_GodMode-On
Agent
Knowledge Discovery Specialist for web research, documentation lookup, and technology evaluation.
cubetribe/ClaudeCode_GodMode-On
Agent
UX Quality Engineer for E2E Testing, Visual Regression, Accessibility, and Performance Audits.
martinkup/symfony-profiler-optimization-advisor-bundle
Agent Claude Code
Subagent creation specialist for designing and configuring new Claude Code subagents. MUST BE USED PROACTIVELY when creating new specialized subagents, modifying existing agent configurations, designing agent system prompts, establishing new development workflow agents, or reviewing agent architecture for consistency…
martinkup/symfony-profiler-optimization-advisor-bundle
Agent Claude Code
Security and privacy compliance auditor for OWASP Top 10 vulnerability assessment and GDPR compliance verification. MUST BE USED PROACTIVELY when reviewing security implementations, conducting vulnerability assessments, verifying privacy compliance, performing threat modeling, or auditing authentication and access…
martinkup/symfony-profiler-optimization-advisor-bundle
Agent Claude Code
PHPUnit testing specialist who creates and maintains tests through comprehensive test strategies, fixture management, and quality validation. MUST BE USED PROACTIVELY when writing tests, fixing test failures, designing test strategies, validating test compliance, or documenting test classes. Can run concurrently with…
Agent
Grounded secretary for Anti-Slop Brain. Use for source-cited questions about detection and repair of AI slop in prose, code, documentation, and agent output, grounded in corpus evidence rather than authorship detection, vault maintenance, claim review, release hygiene, and read-only advisory workflows. Reads the brain…
Agent
Read-only slop grader for prose, documentation and agent output. Returns findings with severity and confidence on separate axes, a verbatim quote for every finding, and the artifact from the structural test that produced it. Never rewrites, never edits, never states or implies who or what wrote the text. Use for a…
Agent
Fresh-context adversarial verifier. Given an artifact and an existing slop review or rewrite, it independently re-checks the claims, the citations, the package names, the scanner results, and the review's own discipline. It tries to break the review rather than confirm it. Reports which findings survive, which are…
Agent
Architecture design agent — evaluates technical solutions, designs system architecture, and reviews architectural decisions. Suitable for new system design or major refactoring.
Agent
Code review agent — systematically reviews code changes and outputs findings according to security → logic → quality → performance priority.
Agent
Security review agent — focuses on OWASP Top 10, key management, input sanitization, dependency vulnerabilities and other security issues.
Agent Claude Code
Reviews code changes for security vulnerabilities.
Agent
Adversarial reviewer for plans and substantial diffs. Reads the actual code/sources and tries to break the work — finds breakage, security/privacy leaks, races, stale assumptions, ordering bugs, and untested gaps. Returns numbered, code-grounded findings. Use before shipping anything high-stakes.